CN109491369A - Performance estimating method, device, equipment and the medium of the practical control unit of vehicle - Google Patents

Performance estimating method, device, equipment and the medium of the practical control unit of vehicle Download PDF

Info

Publication number
CN109491369A
CN109491369A CN201811479522.9A CN201811479522A CN109491369A CN 109491369 A CN109491369 A CN 109491369A CN 201811479522 A CN201811479522 A CN 201811479522A CN 109491369 A CN109491369 A CN 109491369A
Authority
CN
China
Prior art keywords
control unit
ideal
data
vehicle
time period
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
CN201811479522.9A
Other languages
Chinese (zh)
Other versions
CN109491369B (en
Inventor
李祎翔
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.)
Baidu Online Network Technology Beijing Co Ltd
Beijing Baidu Netcom Science and Technology Co Ltd
Original Assignee
Beijing Baidu Netcom Science and Technology 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 Beijing Baidu Netcom Science and Technology Co Ltd filed Critical Beijing Baidu Netcom Science and Technology Co Ltd
Priority to CN201811479522.9A priority Critical patent/CN109491369B/en
Publication of CN109491369A publication Critical patent/CN109491369A/en
Application granted granted Critical
Publication of CN109491369B publication Critical patent/CN109491369B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B23/00Testing or monitoring of control systems or parts thereof
    • G05B23/02Electric testing or monitoring
    • G05B23/0205Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
    • G05B23/0218Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
    • G05B23/0243Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model

Abstract

The embodiment of the invention discloses a kind of performance estimating method of the practical control unit of vehicle, device, equipment and media.It include: based on high-precision map object of planning path, it controls ideal decision-marking planning control module and carries out ideal emulation traveling according to destination path, the layout data of decision rule unit output and the ideal trajectory data and ideal movements status data of ideal control unit output in ideal decision-marking planning control module are acquired in ideal emulation driving process;Decision rule unit is controlled into practical control unit work as the input of practical control unit to be measured in the layout data that first time period exports, and acquires actual path data and actual motion status data that practical control unit exports in second time period;The track data and motion state data exported according to ideal control unit and practical control unit in second time period, the performance of the practical control unit of determination.Improve the assessment efficiency of the practical control unit of vehicle.

Description

Performance estimating method, device, equipment and the medium of the practical control unit of vehicle
Technical field
The present embodiments relate to the Performance Evaluation sides of automatic Pilot technology more particularly to a kind of practical control unit of vehicle Method, device, equipment and medium.
Background technique
During automatic driving vehicle road test, driving path is all non-quantitation, uncontrollable, thus in order to guarantee The driving safety of automatic driving vehicle, carrying out test to practical control algolithm of the automatic driving vehicle under various driving paths is Very necessary.Practical control algolithm is applied to practical control unit, the rule which is exported based on decision rule control module Data are drawn actually to control the traveling of vehicle, currently, usually existing when the practical control module to vehicle carries out recruitment evaluation Before vehicle release to practical control module carry out recruitment evaluation, and for vehicle actual travel during, practical control module It assesses very inefficient.
Summary of the invention
The embodiment of the invention provides a kind of performance estimating method of the practical control unit of vehicle, device, equipment and medium, Different paths can be directed to, emulation survey is carried out to practical control unit based on the data of ideal decision-marking planning control module output Examination, improves the assessment efficiency of the practical control unit of vehicle.
In a first aspect, the embodiment of the invention provides a kind of performance estimating method of the practical control unit of vehicle, this method Include:
Based on high-precision map object of planning path, controls ideal decision-marking planning control module and carried out according to the destination path Ideal emulation travels, and it is defeated to acquire decision rule unit in the ideal decision-marking planning control module in ideal emulation driving process The ideal trajectory data and ideal movements status data of layout data and ideal control unit output out;
The layout data that the decision rule unit is exported in first time period is as practical control unit to be measured Input controls the practical control unit work, and acquires the reality that the practical control unit exports in second time period Track data and actual motion status data, wherein the first time period is before the second time period;
The ideal trajectory data and ideal movements state exported according to the ideal control unit in the second time period The actual path data and actual motion status number that data and the practical control unit are exported in the second time period According to determining the performance of the practical control unit.
Second aspect, the embodiment of the invention also provides a kind of capability evaluating device of the practical control unit of vehicle, the dresses It sets and includes:
Control module is travelled, for being based on high-precision map object of planning path, control ideal decision-marking planning control module is pressed Ideal emulation traveling is carried out according to the destination path;
Ideal data acquisition module, for acquiring the ideal decision-marking planning control module in ideal emulation driving process The layout data of middle decision rule unit output and the ideal trajectory data and ideal movements state of ideal control unit output Data;
Real data acquisition module, layout data for exporting the decision rule unit in first time period as The input of practical control unit to be measured controls the practical control unit and works, and acquires the practical control unit the The actual path data and actual motion status data exported in two periods, wherein the first time period is at described second Between before section;
Performance determining module, the ideal trajectory number for being exported according to the ideal control unit in the second time period According to the actual path data exported with ideal movements status data and the practical control unit in the second time period and Actual motion status data determines the performance of the practical control unit.
The third aspect, the embodiment of the invention also provides a kind of equipment, comprising:
One or more processors;
Storage device, for storing one or more programs;
When one or more of programs are executed by one or more of processors, so that one or more of processing Device realizes the performance estimating method of the practical control unit of vehicle as described in any embodiment of that present invention.
Fourth aspect, the embodiment of the invention also provides a kind of computer readable storage mediums, are stored thereon with computer Program realizes that the performance of the practical control unit of vehicle as described in any embodiment of that present invention is commented when the program is executed by processor Estimate method.
The scheme of the embodiment of the present invention, ideal decision-marking planning control module is in the destination path row planned according to high-precision map During sailing, layout data and ideal trajectory data and ideal movements status data are exported, layout data is inputted practical Control unit obtains actual path data and actual motion status data, and by itself and ideal trajectory data and ideal movements state Data carry out Performance Evaluation to practical control unit together.It realizes for different paths, is based on ideal decision-marking planning control mould The data of block output carry out emulation testing to practical control unit, improve commenting for the practical control unit of automatic driving vehicle Estimate efficiency.
Detailed description of the invention
Fig. 1 is a kind of flow chart of the performance estimating method for the practical control unit of vehicle that the embodiment of the present invention one provides;
Fig. 2 is a kind of flow chart of the performance estimating method of the practical control unit of vehicle provided by Embodiment 2 of the present invention;
Fig. 3 is a kind of structural representation of the capability evaluating device for the practical control unit of vehicle that the embodiment of the present invention three provides Figure;
Fig. 4 is a kind of structural schematic diagram for equipment that the embodiment of the present invention four provides.
Specific embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched The specific embodiment stated is used only for explaining the present invention rather than limiting the invention.It also should be noted that in order to just Only the parts related to the present invention are shown in description, attached drawing rather than entire infrastructure.
Embodiment one
Fig. 1 is the flow chart of the performance estimating method for the practical control unit of vehicle that the embodiment of the present invention one provides, this reality It applies example and is applicable to the case where Performance Evaluation is carried out to the practical control unit of automatic driving vehicle, this method can be by the present invention The capability evaluating device or equipment for the vehicle practical control unit that embodiment provides execute, the device can be used hardware and/or The mode of software is realized, can be only fitted in automatic driving vehicle.As shown in Figure 1, specifically comprising the following steps:
S101, be based on high-precision map object of planning path, control ideal decision-marking planning control module according to destination path into The ideal emulation traveling of row, acquires decision rule unit output in ideal decision-marking planning control module in ideal emulation driving process Layout data and the output of ideal control unit ideal trajectory data and ideal movements status data.
Wherein, high-precision map can be essential map datum in automatic driving vehicle driving process, drive automatically During sailing, high-precision map plays high accuracy positioning, auxiliary environment perception and decision rule control unit is assisted to determine The effects of plan, planning control.It include the details of the roads such as lane line, lane line center line and lane attribute change in high-precision map Information;The curvature of road, the gradient, course, etc. mathematic parameters information;And the roads circuit unit letter such as traffic mark board, land table mark Breath etc..High-precision map can be to download from internet and obtain, and be also possible to the three-dimensional point cloud number acquired based on radar laser device It makes and obtains offline according to the location data with global positioning system.Ideal decision-marking planning control module can be automatic driving vehicle In nucleus module, which may include decision rule unit and ideal control unit, and decision rule unit can be automatic Travel situations current according to high-precision map datum and vehicle in vehicle travel process are driven, generate traveling strategy, and according to this Strategy generating layout data.Ideal control unit can be the perfect layout data for executing decision rule unit and generating, and be managed Think driving trace and ideal movements status data.For example, according to the positioning scenarios of high-precision map and automatic driving vehicle, decision rule It draws unit discovery front to need to turn, and the straight-line travelling that vehicle is current, then can generate the decision instruction of turning, and according to turning Decision instruction generate turning layout data (e.g., the rotary inertia of steering wheel, front wheel angle, rear-wheel corner, speed etc.), it is ideal Control unit perfection executes the layout data, obtains ideal driving trace and motion state data.Control automatic driving vehicle It is travelled according to the turning layout data of generation.
Optionally, in embodiments of the present invention, it is based on high-precision map object of planning path, can be tester automatic It drives after inputting this start position and final position in Vehicular system, system is based on start position and terminal in high-precision map Map datum between position plans the optimum target path of this traveling automatically;It is also possible to tester in automatic Pilot vehicle The destination path planned manually in system based on high-precision map.The destination path may include that left/right turns 45 degree, turn around, The curved mono-/multi- lane etc. of rich eight words.After the completion of destination path planning, automatic driving vehicle controls ideal decision-marking planning control module Ideal emulation traveling is carried out according to the destination path of planning.That is Utopian to be travelled according to destination path, but certainly During dynamic driving vehicle actual travel, vehicle can not be fully according to the destination path desired ride of planning, such as mistake of traveling There are barriers on road in journey, then just need to change driving path detour at this time.Therefore, it is necessary in automatic driving vehicle ideal It emulates in driving process, adjusts the traveling strategy of subsequent time in real time by decision rule control module, it is lower for the moment to generate control The layout data of traveling is carved, and then controls travelling on road for vehicle safety.Specifically, emulating driving process in vehicle ideal In, decision rule unit in ideal decision-marking planning control module can according to current travel situations and current location high-precisionly Diagram data generates the layout data of control automatic driving vehicle subsequent time.Ideal control unit perfection executes the layout data, Obtain ideal trajectory data and ideal movements status data.Wherein, ideal trajectory data are perfect Execution plan data, are obtained Track data, the track data may include at the time of the position coordinates of each tracing point, each tracing point correspond to and the boat of track To etc..Ideal movements state can be perfect Execution plan data, obtain motion state data, which can wrap Include speed and/or corner.
It should be noted that layout data is to provide traveling foundation for the next traveling of automatic driving vehicle, therefore, from The layout data of the dynamic decision rule unit current time output for driving vehicle is actually to control vehicle subsequent time traveling Layout data.Therefore, ideal control unit executes the ideal trajectory data and ideal movements status data of layout data output For the ideal trajectory data and ideal movements status data of subsequent time vehicle.
S102, the layout data that decision rule unit is exported in first time period is as practical control unit to be measured Input controls practical control unit work, and acquires the actual path data that practical control unit exports in second time period With actual motion status data.
Wherein, first time period and second time period can be two adjacent periods, and first time period is second Before period, the layout data that decision rule unit is exported in first time period is to control automatic driving vehicle Two periods used when driving.For example, current time decision rule unit, which analyzes vehicle front, barrier, then it can generate and subtract Fast avoidance strategy, the layout datas such as the control vehicle deceleration of generation, steering, and the layout datas such as slow down, turn to are to control Vehicle slows down and Turning travel when driving in subsequent time.Practical control unit can be practical control automatic driving vehicle traveling Control unit.The control unit is compared with ideal control unit, it is contemplated that the kinetic effect of vehicle actual travel process Factor, when executing the layout data of decision rule unit output, it is contemplated that the influence of kinetic factor guarantees as far as possible Vehicle is travelled according to the understanding track of ideal control unit and motion state.
Specifically, decision rule unit in S101 is used to control vehicle second time period row what first time period exported Input of the layout data sailed as practical control unit to be tested, to control practical control unit according to the planning number of input According to control automatic driving vehicle traveling, practical control unit is then acquired by data acquisition unit and controls automatic driving vehicle row When sailing, the actual path data and actual motion status data of vehicle output.Wherein, the actual path data and actual motion shape State data are substantially the actual path data and actual motion shape of the corresponding second time period of layout data of first time period State data.Optionally, data acquisition unit acquires the actual path data and actual motion status number of practical control unit output Collection period is determined according to can be according to the calculating frequency of practical control unit control algolithm, for example, if the meter of control algolithm Calculating frequency is 10Hz/s, then, it is primary that the sampling period can be 1s acquisition.
S103, the ideal trajectory data exported according to ideal control unit in second time period and ideal movements status number According to, and the actual path data that export in second time period of practical control unit and actual motion status data, it determines practical The performance of control unit.
Optionally, automatic driving vehicle the layout data exported based on decision rule unit when driving, since vehicle is dynamic The influence of mechanics or actual environment situation, vehicle can not can guarantee the actual path data and practical fortune of practical control unit output The ideal trajectory data and ideal movements status data of dynamic status data and ideal control unit perfection Execution plan data output It is completely the same.For example, layout data is 30 degree of corner, the corner of ideal control unit perfection Execution plan data output is 30 Degree, and actually due to the influence of frictional resistance, practical control unit control vehicle actual rotational angle only has 25 degree.It can be according to reality Departure degree between track and actual motion status data and ideal trajectory and ideal movements status data, to determine practical control The performance of unit processed, and then complete the Performance Evaluation to practical control unit.
Optionally, in embodiments of the present invention, according to ideal control unit and practical control unit in second time period The performance of practical control unit is divided into track when determining the performance of practical control unit by track data and motion state data Data output performance and motion state data output performance are assessed, and such as can be ideal control unit in second time period The ideal trajectory data and practical control unit of output are compared in the actual path data that second time period exports, and determine two The similarity degree of track data, and then obtain the track data output performance of practical control unit;By ideal control unit The actual motion status number that the ideal movements status data of two periods output and practical control unit are exported in second time period According to being compared, the similarity degree of two motion state datas is determined, and then the motion state data for obtaining practical control unit is defeated Performance out.It is also possible to the track data output performance and motion state data output performance in conjunction with practical control unit, assessment The overall performance of practical control unit.Such as can be track data output performance and motion state output performance are brought into it is preset In overall performance calculation formula, the overall performance of practical control unit is calculated;It can also be as track data output performance and fortune Different weighted values is arranged in dynamic status data output performance, calculates track data output performance and motion state data output performance Weighting performance, the overall performance as practical control unit.
Illustratively, it would be desirable to which control unit exists in the ideal trajectory data that second time period exports with practical control unit The actual path data of second time period output are compared, and determine the similarity degree of two track datas, and then obtain practical control The track data output performance of unit processed may is that and calculate the distance between actual path data and ideal trajectory data mean value (it such as can be the distance difference for calculating corresponding each tracing point in two track datas, determine the distance difference of all tracing points Average value), according to apart from mean value and preset criterion, judge that practical control unit is corresponding in output trajectory data Performance Evaluation situation, it is such as smaller apart from mean value, illustrate practical control unit corresponding Performance Evaluation effect in output trajectory data Fruit is better;It is also possible to determine practical control unit corresponding property in output trajectory data by way of track drafting figure It can assessment result.Specifically, may include steps of:
A, the ideal trajectory data exported according to ideal control unit in second time period draw the first trajectory diagram.
Specifically, building abscissa is each time in second time period, ordinate is the track of ideal trajectory point position Figure, it would be desirable to each track point data in track data is labeled in trajectory diagram according to its corresponding time and track position, It carries out curve fitting to each tracing point being labeled in trajectory diagram, obtains ideal trajectory datagram, i.e. the first trajectory diagram.It is optional , when drawing the first trajectory diagram, it can be and pass through curve fitting software, it would be desirable to which it is soft that track data is input to the curve matching In part, which will be fitted according to the ideal trajectory data of input and obtain corresponding first trajectory diagram of the data.
B, the actual path data exported according to practical control unit in second time period draw the second trajectory diagram.
Specifically, can be based on actual path data, building abscissa is second time period when drawing the second trajectory diagram Interior each time, ordinate are the actual path datagram of actual path point position, i.e. the second trajectory diagram specifically draws mode This can no longer be repeated as the first trajectory diagram of drafting.
C, according to the concordance rate between the first trajectory diagram and the second trajectory diagram, the performance of practical control unit is determined.
Specifically, judging the concordance rate between the first trajectory diagram and the second trajectory diagram, the concordance rate of two trajectory diagrams is higher, says Bright practical control unit corresponding Performance Evaluation effect in output trajectory data is better.Optionally, judge the first trajectory diagram and When concordance rate between the second trajectory diagram, coincidence factor, the error rate by calculating the first trajectory diagram and the second trajectory diagram can be Etc. modes judge.
Illustratively, it would be desirable to the ideal movements status data and practical control list that control unit is exported in second time period Member is compared in the actual motion status data that second time period exports, and determines the similarity degree of two motion state datas, into And the motion state data output performance of practical control unit is obtained, it may is that according to the ideal control unit described the The ideal movements status data of two periods output, the practical fortune exported with the practical control unit in the second time period Concordance rate between dynamic status data, determines the performance of the practical control unit.Specifically, can be actual motion state At least one of speed and/or corner in data, in corresponding speed in ideal movements status data and/or corner At least one is compared, and to determine the similarity degree of actual motion status data and ideal movements status data, obtains reality The motion state data output performance of control unit.It such as can be that similarity degree is higher, then the motion state of practical control unit Data output performance is better.It can also be that different weighted values is arranged in speed and corner in respectively motion state data, (such as It can be the significance level shared in practical control unit control vehicle travel process according to motion state data to come for difference The data of type different weighted values is set);Then calculate again actual motion status data and ideal movements status data it Between weighting similarity degree, according to motion state data output performance of the weighting similarity degree as practical control unit.
Optionally, in the embodiment of the present invention, compare two track datas consistency and two motion states consistency when, can To be consistency that comparison corresponds to time and/or corresponding specific value.For example, it may be compare in two track datas it is mutually right Whether the correspondence time for each tracing point answered consistent and/or two track datas in mutual corresponding each tracing point corresponding position It is whether consistent.
Optionally, in the ideal trajectory data and ideal movements state exported according to ideal control unit in second time period Data, and the actual path data that export in second time period of practical control unit and actual motion status data, determine real When the performance of border control unit, it can also be using preparatory trained performance test model and determine the property of practical control unit Energy.Specifically, can be ideal trajectory data, ideal movements status data, actual path data and actual motion status number According to all inputting in advance in trained performance test model, algorithm when which can be according to training, to the data of input into Row analysis, exports the results of performance analysis to practical control unit.Wherein, performance test model can be pre- first pass through largely Multiple groups ideal trajectory data, ideal movements status data, actual path data and actual motion under different paths, different scenes The results of performance analysis of status data and the corresponding practical control unit of every group of data is as sample data, by using more Kind neural network algorithm obtains neural network model training.
Optionally, in order to improve the accuracy of practical control unit Performance Evaluation, can be planned based on high-precision map it is more The different destination path of kind, is performed a plurality of times the above method under a variety of different destination paths, determines practical control unit not With the performance under destination path.According to the performance evaluation result of the practical control unit repeatedly determined, analysis obtains practical control The final performance evaluation result of unit.
Present embodiments provide a kind of performance estimating method of practical control unit of vehicle, ideal decision-marking planning control module During the destination path traveling planned according to high-precision map, layout data and ideal trajectory data and ideal fortune are exported Layout data is inputted practical control unit and obtains actual path data and actual motion status data by dynamic status data, and will It carries out Performance Evaluation to practical control unit together with ideal trajectory data and ideal movements status data.It realizes for not Same path is carried out emulation testing to practical control unit, is improved certainly based on the data of ideal decision-marking planning control module output The assessment efficiency of the dynamic practical control unit for driving vehicle.
Embodiment two
Fig. 2 is a kind of flow chart of the performance estimating method of the practical control unit of vehicle provided by Embodiment 2 of the present invention, This method further optimizes on the basis of the above embodiments, shows in particular and comments in the progress practical control unit performance of vehicle Before estimating, the detailed process introduction of the practical control unit of automatic driving vehicle is formed.As shown in Fig. 2, this method comprises:
S201 constructs vehicle dynamic model according to the static attribute parameter of vehicle.
Wherein, static attribute parameter can be cause decision rule controlling value with vehicle driving real output value there are errors The preset parameter that carries of vehicle itself.For example, may include vehicle empty mass, car gage and vehicle wheelbase etc..Vehicle When empty mass can be vehicle and not carry any object, the quality of vehicle itself;The wheelspan of vehicle can be right on vehicle Claim the distance between the left and right two-wheeled of setting;The wheelbase of vehicle can be ipsilateral the distance between the front and back two-wheeled of vehicle.Vehicle Kinetic model can be to study the relationship of stress condition and vehicle movement acted on vehicle and the model established, can be with Including 1/4 model of 2DOF, 7 freedom degree, 1/2 model and 15 freedom degree whole vehicle models etc..
Optionally, when constructing vehicle dynamic model according to the static attribute parameter of vehicle, can be analysis leads to ideal Output valve and real output value the reason of there are errors, so that it is determined that setting about being joined according to the static attribute of vehicle from which freedom degree Number, building meet the vehicle dynamic model of current automatic Pilot wheel;It is also possible to using in existing kinetic theory Existing vehicle dynamic model (such as 1/4 model of 2DOF, 7 freedom degree, 1/2 model or 15 freedom degree whole vehicle models), in conjunction with The static attribute parameter of current automatic driving vehicle, constructs the vehicle dynamic model of current automatic driving vehicle, for example, can be with The static attribute parameter for the vehicle that will acquire imports in third party's dynamics software, and software can construct this automatically and drive automatically Sail the vehicle dynamic model of vehicle.
Optionally, when constructing vehicle dynamic model according to the static attribute parameter of vehicle, can be to same model or Vehicle constitutes similar a kind of automatic driving vehicle and constructs a kind of vehicle dynamic model.
S202 is right according to relationship of the vehicle between the vehicle actual travel parameter acquired in road actual moving process Vehicle dynamic model is calibrated, and practical control unit is formed.
Wherein, vehicle actual travel parameter can refer to the row that automatic driving vehicle exports in road actual moving process Parameter is sailed, may include: acceleration, speed, throttle, brake, rotary inertia of steering wheel, the torque, friction of automatic driving vehicle Force coefficient, front wheel angle, rear-wheel corner, full-vehicle steering error etc..
The vehicle dynamic model of S201 building causes vehicle dynamic due to measurement error or running environment difference in order to prevent The situation of the parameter inaccuracy of mechanical model occurs, and before generating practical control unit based on vehicle dynamic model, needs elder generation The vehicle dynamic model of building is calibrated, the error because of vehicle dynamic model is avoided to lead to the practical control list generated The situation of first performance difference occurs.
Optionally, usually there is certain corresponding relationships between collected vehicle actual travel parameter, for example, accelerating Degree and the relationship between the relationship between speed, throttle, rotary inertia of steering wheel and front wheel angle, rear-wheel corner etc..At this It, can be by the relationship during automatic driving vehicle actual travel between the driving parameters of output, to vehicle in inventive embodiments Kinetic model is calibrated, for example, can be according to the relationship between acceleration and speed, throttle, to dynamics of vehicle mould Model formation parameter relevant with acceleration, speed, throttle is adjusted in type.The practical row of automatic driving vehicle can also be passed through The relationship between driving parameters that exports during sailing and by the kinetic model of the vehicle by ideal decision-marking planning control Relationship between the desired ride parameter of module planning, to be calibrated to vehicle dynamic model.Specifically, can be basis Relationship between the desired ride parameter of relationship and planning between actual travel parameter is compared, and adjusts dynamics of vehicle mould Parameter value in type, and then complete the calibration to vehicle dynamic model;It is also possible to according to the pass between actual travel parameter The relationship between driving parameters that system and emulation testing obtain, constructs cost function, acquires corresponding dynamics when error minimum Model formation parameter, and then complete the calibration to vehicle dynamic model;It can also be based on neural network model, by practical row Sail the relationship input neural network model between the relationship between parameter and the desired ride parameter of planning, the neural network model Sample data and the corresponding optimal value of the parameter of corresponding algorithm analysis output power model when can be according to training, thus complete The calibration of pairs of vehicle dynamic model.It should be noted that the embodiment of the present invention can also be using other modes according to vehicle Relationship between the vehicle actual travel parameter acquired in road actual moving process, carries out school to vehicle dynamic model Standard, to this present embodiment without limiting.
Optionally, after vehicle dynamic model calibration, automatic driving vehicle can be formed based on the vehicle dynamic model In practical control unit, the practical control unit constructed in this way avoids the static attribute parameter and vehicle power because of vehicle The case where factor causes the output of ideal control unit in reality output and ideal decision-marking planning control module to have differences.It mentions High accuracy of the practical control unit according to layout data output result.Specifically, according to the dynamics of vehicle mould after calibration Type may is that when forming practical control unit the corresponding formula of vehicle dynamic model after calibration being embedded into practical control It, be first based on the vehicle in control algolithm for each layout data inputted in practical control unit in the control algolithm of unit After kinetic model formula manipulation, in the traveling for being used to control automatic driving vehicle.
S203, be based on high-precision map object of planning path, control ideal decision-marking planning control module according to destination path into The ideal emulation traveling of row, acquires decision rule unit output in ideal decision-marking planning control module in ideal emulation driving process Layout data and the output of ideal control unit ideal trajectory data and ideal movements status data.
S204, the layout data that decision rule unit is exported in first time period is as practical control unit to be measured Input controls practical control unit work, and acquires the actual path data that practical control unit exports in second time period With actual motion status data.
S205, the ideal trajectory data exported according to ideal control unit in second time period and ideal movements status number According to, and the actual path data that export in second time period of practical control unit and actual motion status data, it determines practical The performance of control unit.
The performance estimating method for present embodiments providing a kind of practical control unit of vehicle, by constructing dynamics of vehicle mould Type, and the practical control unit of vehicle is generated after calibrating to the vehicle dynamic model of building, to practical control unit When carrying out Performance Evaluation, ideal decision-marking planning control module exports layout data and ideal trajectory data and ideal movements state Layout data is inputted practical control unit and obtains actual path data and actual motion status data by data, and by itself and reason Think that track data and ideal movements status data carry out the assessment of practical control unit performance together.Practical control can generated Guarantee the accuracy of its control when unit as far as possible, is then directed to different paths again, it is defeated based on ideal decision-marking planning control module Data out carry out emulation testing to practical control unit, improve the assessment efficiency of the practical control unit of vehicle, and then improve The safety of automatic driving vehicle traveling.
Embodiment three
Fig. 3 is a kind of structural representation of the capability evaluating device for the practical control unit of vehicle that the embodiment of the present invention three provides Figure, the device can be performed the performance estimating method of the practical control unit of vehicle provided by any embodiment of the invention, have and hold The corresponding functional module of row method and beneficial effect, are configurable in automatic driving vehicle.As shown in figure 3, the device includes:
Control module 301 is travelled, for being based on high-precision map object of planning path, controls ideal decision-marking planning control module Ideal emulation traveling is carried out according to the destination path;
Ideal data acquisition module 302, for acquiring the ideal decision-marking planning control in ideal emulation driving process The ideal trajectory data and ideal movements of decision rule unit exports in module layout data and ideal control unit output Status data;
Real data acquisition module 303, the layout data for exporting the decision rule unit in first time period As the input of practical control unit to be measured, the practical control unit work is controlled, and acquires the practical control unit The actual path data and actual motion status data exported in second time period, wherein the first time period is described Before two periods;
Performance determining module 304, the ideal rail for being exported according to the ideal control unit in the second time period The actual path number that mark data and ideal movements status data and the practical control unit are exported in the second time period According to actual motion status data, determine the performance of the practical control unit.
Present embodiments provide a kind of capability evaluating device of practical control unit of vehicle, ideal decision-marking planning control module During the destination path traveling planned according to high-precision map, layout data and ideal trajectory data and ideal fortune are exported Layout data is inputted practical control unit and obtains actual path data and actual motion status data by dynamic status data, and will It carries out Performance Evaluation to practical control unit together with ideal trajectory data and ideal movements status data.It realizes for not Same path is carried out emulation testing to practical control unit, is improved certainly based on the data of ideal decision-marking planning control module output The assessment efficiency of the dynamic practical control unit for driving vehicle.
Further, above-mentioned performance determining module 304 is specifically used for:
According to the ideal trajectory data that the ideal control unit is exported in the second time period, the first track is drawn Figure;
According to the actual path data that the practical control unit is exported in the second time period, the second track is drawn Figure;
According to the concordance rate between the first trajectory diagram and the second trajectory diagram, the performance of the practical control unit is determined.
Further, above-mentioned performance determining module 304 is specifically used for:
According to the ideal movements status data that the ideal control unit is exported in the second time period, with the reality Concordance rate of the control unit between the actual motion status data that the second time period exports determines that the practical control is single The performance of member;Wherein ideal movements status data and actual motion status data include speed and/or corner.
Further, above-mentioned apparatus further includes that actual cell forms module, is used for:
Vehicle dynamic model is constructed according to the static attribute parameter of vehicle;
According to relationship of the vehicle between the vehicle actual travel parameter acquired in road actual moving process, to institute It states vehicle dynamic model to be calibrated, forms the practical control unit
Example IV
Fig. 4 is a kind of structural schematic diagram for equipment that the embodiment of the present invention four provides.Fig. 4, which is shown, to be suitable for being used to realizing this The block diagram of the example devices 40 of invention embodiment.The equipment 40 that Fig. 4 is shown is only an example, should not be to of the invention real The function and use scope for applying example bring any restrictions.As shown in figure 4, the equipment 40 is showed in the form of universal computing device. The component of the equipment 40 can include but is not limited to: one or more processor or processing unit 401, system storage 402, connect the bus 403 of different system components (including system storage 402 and processing unit 401).
Bus 403 indicates one of a few class bus structures or a variety of, including memory bus or Memory Controller, Peripheral bus, graphics acceleration port, processor or the local bus using any bus structures in a variety of bus structures.It lifts For example, these architectures include but is not limited to industry standard architecture (ISA) bus, microchannel architecture (MAC) Bus, enhanced isa bus, Video Electronics Standards Association (VESA) local bus and peripheral component interconnection (PCI) bus.
Equipment 40 typically comprises a variety of computer system readable media.These media can be it is any can be by equipment 40 The usable medium of access, including volatile and non-volatile media, moveable and immovable medium.
System storage 402 may include the computer system readable media of form of volatile memory, such as deposit at random Access to memory (RAM) 404 and/or cache memory 405.Equipment 40 may further include other removable/not removable Dynamic, volatile/non-volatile computer system storage medium.Only as an example, storage system 406 can be used for read and write can not Mobile, non-volatile magnetic media (Fig. 4 do not show, commonly referred to as " hard disk drive ").Although not shown in fig 4, Ke Yiti For the disc driver for being read and write to removable non-volatile magnetic disk (such as " floppy disk "), and to moving non-volatile light The CD drive of disk (such as CD-ROM, DVD-ROM or other optical mediums) read-write.In these cases, each driver It can be connected by one or more data media interfaces with bus 403.System storage 402 may include at least one journey Sequence product, the program product have one group of (for example, at least one) program module, these program modules are configured to perform this hair The function of bright each embodiment.
Program/utility 408 with one group of (at least one) program module 407, can store and deposit in such as system In reservoir 402, such program module 407 includes but is not limited to operating system, one or more application program, other programs It may include the realization of network environment in module and program data, each of these examples or certain combination.Program mould Block 407 usually executes function and/or method in embodiment described in the invention.
Equipment 40 can also be logical with one or more external equipments 409 (such as keyboard, sensing equipment, display 410 etc.) Letter, can also be enabled a user to one or more equipment interact with the equipment communicate, and/or with enable the equipment 40 with One or more of the other any equipment (such as network interface card, modem etc.) communication for calculating equipment and being communicated.It is this logical Letter can be carried out by input/output (I/O) interface 411.Also, equipment 40 can also pass through network adapter 412 and one Or multiple networks (such as local area network (LAN), wide area network (WAN) and/or public network, such as internet) communication.Such as Fig. 4 institute Show, network adapter 412 is communicated by bus 403 with other modules of equipment 40.It should be understood that although not shown in the drawings, can Other hardware and/or software module are used with bonding apparatus 40, including but not limited to: microcode, device driver, redundancy processing Unit, external disk drive array, RAID system, tape drive and data backup storage system etc..
Processing unit 401 by the program that is stored in system storage 402 of operation, thereby executing various function application with And data processing, such as realize the performance estimating method of the practical control unit of vehicle provided by the embodiment of the present invention.
Embodiment five
The embodiment of the present invention five additionally provides a kind of computer readable storage medium, is stored thereon with computer program, should Program can realize the performance estimating method of the practical control unit of vehicle described in above-described embodiment when being executed by processor.
The computer storage medium of the embodiment of the present invention, can be using any of one or more computer-readable media Combination.Computer-readable medium can be computer-readable signal media or computer readable storage medium.It is computer-readable Storage medium can be for example but not limited to: electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor system, device or device, or Any above combination of person.The more specific example (non exhaustive list) of computer readable storage medium includes: with one Or the electrical connections of multiple conducting wires, portable computer diskette, hard disk, random access memory (RAM), read-only memory (ROM), Erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light Memory device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer readable storage medium can With to be any include or the tangible medium of storage program, the program can be commanded execution system, device or device use or Person is in connection.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal, Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including but unlimited In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can Any computer-readable medium other than storage medium is read, which can send, propagates or transmit and be used for By the use of instruction execution system, device or device or program in connection.
The program code for including on computer-readable medium can transmit with any suitable medium, including but not limited to: Wirelessly, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
The computer for executing operation of the present invention can be write with one or more programming languages or combinations thereof Program code, described program design language include object oriented program language, such as Java, Smalltalk, C++, also Including conventional procedural programming language-such as " C " language or similar programming language.Program code can be complete It executes, partly executed on the user computer on the user computer entirely, being executed as an independent software package, part Part executes on the remote computer or executes on a remote computer or server completely on the user computer.It is relating to And in the situation of remote computer, remote computer can pass through the network of any kind, including local area network (LAN) or wide area network (WAN), it is connected to subscriber computer, or, it may be connected to outer computer (such as led to using ISP Cross internet connection).
Above-described embodiment serial number is for illustration only, does not represent the advantages or disadvantages of the embodiments.
Will be appreciated by those skilled in the art that each module of the above-mentioned embodiment of the present invention or each operation can be used and lead to Computing device realizes that they can be concentrated on single computing device, or be distributed in multiple computing devices and formed Network on, optionally, they can be realized with the program code that computer installation can be performed, so as to storing them Be performed by computing device in the storage device, perhaps they are fabricated to each integrated circuit modules or by they In multiple modules or operation be fabricated to single integrated circuit module to realize.In this way, the present invention is not limited to any specific The combination of hardware and software.
All the embodiments in this specification are described in a progressive manner, the highlights of each of the examples are with The difference of other embodiments, the same or similar part between each embodiment may refer to each other.
The above description is only a preferred embodiment of the present invention, is not intended to restrict the invention, for those skilled in the art For, the invention can have various changes and changes.All any modifications made within the spirit and principles of the present invention are equal Replacement, improvement etc., should all be included in the protection scope of the present invention.

Claims (10)

1. a kind of performance estimating method of the practical control unit of vehicle characterized by comprising
Based on high-precision map object of planning path, ideal decision-marking planning control module is controlled according to the destination path and carries out ideal Emulation traveling acquires what decision rule unit in the ideal decision-marking planning control module exported in ideal emulation driving process Layout data and the ideal trajectory data and ideal movements status data of ideal control unit output;
The layout data that the decision rule unit is exported in first time period as the input of practical control unit to be measured, The practical control unit work is controlled, and acquires the actual path number that the practical control unit exports in second time period According to actual motion status data, wherein the first time period is before the second time period;
The ideal trajectory data and ideal movements status data exported according to the ideal control unit in the second time period, And the actual path data that export in the second time period of the practical control unit and actual motion status data, it determines The performance of the practical control unit.
2. the method according to claim 1, wherein according to the ideal control unit in the second time period The actual path data that the ideal trajectory data of output and the practical control unit are exported in the second time period, determine institute State the performance of practical control unit, comprising:
According to the ideal trajectory data that the ideal control unit is exported in the second time period, the first trajectory diagram is drawn;
According to the actual path data that the practical control unit is exported in the second time period, the second trajectory diagram is drawn;
According to the concordance rate between the first trajectory diagram and the second trajectory diagram, the performance of the practical control unit is determined.
3. the method according to claim 1, wherein according to the ideal control unit in the second time period The actual motion status number that the ideal movements status data of output and the practical control unit are exported in the second time period According to determining the performance of the practical control unit, comprising:
According to the ideal movements status data that the ideal control unit is exported in the second time period, with the practical control Concordance rate of the unit between the actual motion status data that the second time period exports, determines the practical control unit Performance;Wherein ideal movements status data and actual motion status data include speed and/or corner.
4. the method according to claim 1, wherein the method is by the decision rule unit at the first time Before input of the motion state data of section output as practical control unit to be measured, further includes:
Vehicle dynamic model is constructed according to the static attribute parameter of vehicle;
According to relationship of the vehicle between the vehicle actual travel parameter acquired in road actual moving process, to the vehicle Kinetic model is calibrated, and the practical control unit is formed.
5. a kind of capability evaluating device of the practical control unit of vehicle characterized by comprising
Control module is travelled, for being based on high-precision map object of planning path, controls ideal decision-marking planning control module according to institute It states destination path and carries out ideal emulation traveling;
Ideal data acquisition module, for being acquired in the ideal decision-marking planning control module certainly in ideal emulation driving process The layout data of plan planning unit output and the ideal trajectory data and ideal movements status data of ideal control unit output;
Real data acquisition module, the layout data for exporting the decision rule unit in first time period is as to be measured Practical control unit input, control the practical control unit and work, and acquire the practical control unit at second Between the actual path data that export in section and actual motion status data, wherein the first time period is in the second time period Before;
Performance determining module, ideal trajectory data for export according to the ideal control unit in the second time period with The actual path data and reality that ideal movements status data and the practical control unit are exported in the second time period Motion state data determines the performance of the practical control unit.
6. device according to claim 5, which is characterized in that the performance determining module is specifically used for:
According to the ideal trajectory data that the ideal control unit is exported in the second time period, the first trajectory diagram is drawn;
According to the actual path data that the practical control unit is exported in the second time period, the second trajectory diagram is drawn;
According to the concordance rate between the first trajectory diagram and the second trajectory diagram, the performance of the practical control unit is determined.
7. device according to claim 5, which is characterized in that the performance determining module is specifically used for:
According to the ideal movements status data that the ideal control unit is exported in the second time period, with the practical control Concordance rate of the unit between the actual motion status data that the second time period exports, determines the practical control unit Performance;Wherein ideal movements status data and actual motion status data include speed and/or corner.
8. device according to claim 5, which is characterized in that further include that actual cell forms module, be used for:
Vehicle dynamic model is constructed according to the static attribute parameter of vehicle;
According to relationship of the vehicle between the vehicle actual travel parameter acquired in road actual moving process, to the vehicle Kinetic model is calibrated, and the practical control unit is formed.
9. a kind of equipment characterized by comprising
One or more processors;
Storage device, for storing one or more programs;
When one or more of programs are executed by one or more of processors, so that one or more of processors are real The now performance estimating method of the practical control unit of vehicle as described in any in claim 1-4.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor The performance estimating method of the practical control unit of vehicle as described in any in claim 1-4 is realized when execution.
CN201811479522.9A 2018-12-05 2018-12-05 Method, device, equipment and medium for evaluating performance of vehicle actual control unit Active CN109491369B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811479522.9A CN109491369B (en) 2018-12-05 2018-12-05 Method, device, equipment and medium for evaluating performance of vehicle actual control unit

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811479522.9A CN109491369B (en) 2018-12-05 2018-12-05 Method, device, equipment and medium for evaluating performance of vehicle actual control unit

Publications (2)

Publication Number Publication Date
CN109491369A true CN109491369A (en) 2019-03-19
CN109491369B CN109491369B (en) 2020-11-17

Family

ID=65699328

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811479522.9A Active CN109491369B (en) 2018-12-05 2018-12-05 Method, device, equipment and medium for evaluating performance of vehicle actual control unit

Country Status (1)

Country Link
CN (1) CN109491369B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109883448A (en) * 2019-03-28 2019-06-14 北京经纬恒润科技有限公司 Map box test method and system
CN110162023A (en) * 2019-06-24 2019-08-23 北京智行者科技有限公司 A kind of test method of control module

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1544760A2 (en) * 2003-12-18 2005-06-22 Nissan Motor Company, Limited Three dimensional road-vehicle modeling system
CN102323761A (en) * 2011-07-18 2012-01-18 铁道部运输局 Semi-physical simulation testing platform of train control network
CN104460349A (en) * 2014-11-28 2015-03-25 北京经纬恒润科技有限公司 Real automobile in-the-loop simulation testing method, real-time simulation machine and system
CN104536434A (en) * 2014-12-15 2015-04-22 华晨汽车集团控股有限公司 Vehicle network bus simulation and testing method
CN104932268A (en) * 2015-06-08 2015-09-23 武汉理工大学 Fuzzy PID based automobile cruise control system
CN105223832A (en) * 2014-06-25 2016-01-06 南车株洲电力机车研究所有限公司 Locomotive hardware-in-the-loop simulation device, system and method
CN105573296A (en) * 2016-01-15 2016-05-11 上海汽车变速器有限公司 Hardware-in-loop-based automation test system for automobile diagnosis, and method thereof
CN105807750A (en) * 2014-12-30 2016-07-27 株洲南车时代电气股份有限公司 Semi-physical simulation test device and test method for transmission control unit of urban rail vehicle
CN107992016A (en) * 2016-10-26 2018-05-04 法乐第(北京)网络科技有限公司 A kind of automatic driving vehicle analog detection method
US20180239342A1 (en) * 2017-02-22 2018-08-23 Electronics And Telecommunications Research Institute Method and apparatus for registering virtual equipment for virtual production system
CN108829087A (en) * 2018-07-19 2018-11-16 山东省科学院自动化研究所 A kind of intelligent test system and test method of autonomous driving vehicle

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1544760A2 (en) * 2003-12-18 2005-06-22 Nissan Motor Company, Limited Three dimensional road-vehicle modeling system
CN102323761A (en) * 2011-07-18 2012-01-18 铁道部运输局 Semi-physical simulation testing platform of train control network
CN105223832A (en) * 2014-06-25 2016-01-06 南车株洲电力机车研究所有限公司 Locomotive hardware-in-the-loop simulation device, system and method
CN104460349A (en) * 2014-11-28 2015-03-25 北京经纬恒润科技有限公司 Real automobile in-the-loop simulation testing method, real-time simulation machine and system
CN104536434A (en) * 2014-12-15 2015-04-22 华晨汽车集团控股有限公司 Vehicle network bus simulation and testing method
CN105807750A (en) * 2014-12-30 2016-07-27 株洲南车时代电气股份有限公司 Semi-physical simulation test device and test method for transmission control unit of urban rail vehicle
CN104932268A (en) * 2015-06-08 2015-09-23 武汉理工大学 Fuzzy PID based automobile cruise control system
CN105573296A (en) * 2016-01-15 2016-05-11 上海汽车变速器有限公司 Hardware-in-loop-based automation test system for automobile diagnosis, and method thereof
CN107992016A (en) * 2016-10-26 2018-05-04 法乐第(北京)网络科技有限公司 A kind of automatic driving vehicle analog detection method
US20180239342A1 (en) * 2017-02-22 2018-08-23 Electronics And Telecommunications Research Institute Method and apparatus for registering virtual equipment for virtual production system
CN108829087A (en) * 2018-07-19 2018-11-16 山东省科学院自动化研究所 A kind of intelligent test system and test method of autonomous driving vehicle

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109883448A (en) * 2019-03-28 2019-06-14 北京经纬恒润科技有限公司 Map box test method and system
CN110162023A (en) * 2019-06-24 2019-08-23 北京智行者科技有限公司 A kind of test method of control module

Also Published As

Publication number Publication date
CN109491369B (en) 2020-11-17

Similar Documents

Publication Publication Date Title
US20190004518A1 (en) Method and system for training unmanned aerial vehicle control model based on artificial intelligence
CN109491369A (en) Performance estimating method, device, equipment and the medium of the practical control unit of vehicle
CN107063711A (en) Method and apparatus for testing unmanned vehicle
CN107991898A (en) A kind of automatic driving vehicle simulating test device and electronic equipment
CN108681264A (en) A kind of intelligent vehicle digitalized artificial test device
CN107992016A (en) A kind of automatic driving vehicle analog detection method
CN106406124B (en) A kind of adhesion control program quick on-line testing method and test module automatically
WO2019065409A1 (en) Automatic driving simulator and map generation method for automatic driving simulator
CN109583776A (en) A kind of vehicle body-sensing evaluating method, device, electronic equipment, medium and vehicle
CN105068857B (en) A kind of driving behavior data capture method based on high fidelity driving simulator
Lamotte et al. Submicroscopic and physics simulation of autonomous and intelligent vehicles in virtual reality
CN109522673A (en) A kind of test method, device, equipment and storage medium
CN109358526A (en) The software of automatic Pilot tracking algorithm based on emulation is in ring test method
Chen et al. A novel integrated simulation and testing platform for self-driving cars with hardware in the loop
CN109345596A (en) Multisensor scaling method, device, computer equipment, medium and vehicle
CN108958066A (en) Emulation test method and device
CN109446662A (en) Generation method and device, the computer equipment and storage medium of vehicle simulation track
CN109211575A (en) Pilotless automobile and its field test method, apparatus and readable medium
JP2021514883A (en) Systems and methods for determining travel routes in autonomous driving
CN109765803A (en) A kind of the simulation hardware test macro and method of the synchronic sky of the more ICU of autonomous driving vehicle
CN110197027A (en) A kind of automatic Pilot test method, device, smart machine and server
CN103236084B (en) A kind of dynamic modelling method of extensive track circuit
CN105956214B (en) A kind of virtual calculation method to gauges of bullet train
CN109435955A (en) A kind of automated driving system performance estimating method, device, equipment and storage medium
CN109297725A (en) Test method, device, equipment, medium and the vehicle of vehicle boundary ability

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