CN112580201A - Simulation test evaluation method and evaluation system for vehicle emergency steering auxiliary system - Google Patents

Simulation test evaluation method and evaluation system for vehicle emergency steering auxiliary system Download PDF

Info

Publication number
CN112580201A
CN112580201A CN202011464279.0A CN202011464279A CN112580201A CN 112580201 A CN112580201 A CN 112580201A CN 202011464279 A CN202011464279 A CN 202011464279A CN 112580201 A CN112580201 A CN 112580201A
Authority
CN
China
Prior art keywords
vehicle
test
target
evaluation
simulation
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
CN202011464279.0A
Other languages
Chinese (zh)
Other versions
CN112580201B (en
Inventor
聂琦
张宇探
罗丰山
刘永臣
刘鹏
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 Corp
Original Assignee
Dongfeng Motor Corp
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 Corp filed Critical Dongfeng Motor Corp
Priority to CN202011464279.0A priority Critical patent/CN112580201B/en
Publication of CN112580201A publication Critical patent/CN112580201A/en
Application granted granted Critical
Publication of CN112580201B publication Critical patent/CN112580201B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Hardware Design (AREA)
  • Evolutionary Computation (AREA)
  • Geometry (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Steering Control In Accordance With Driving Conditions (AREA)

Abstract

The invention discloses a simulation test evaluation method of a vehicle emergency steering auxiliary ESA system, which comprises the following steps: carrying out simulation test on the ESA system to obtain first test result parameters corresponding to the M first evaluation indexes and second test result parameters corresponding to the N second evaluation indexes; judging whether all the first test result parameters are qualified or not according to the first target result parameters, and outputting Boolean value scores representing whether the simulation tests pass or not; when the first test result parameters are all qualified, evaluating the second test result parameters according to the second target result parameters to obtain a single score corresponding to each second evaluation index; determining the weighted score of the ESA system according to the single score and the weight coefficient; adjusting the ESA system according to at least one of the Boolean value score, the single item score and the weighted score; the method can obviously improve the evaluation efficiency of the simulation result of the ESA system.

Description

Simulation test evaluation method and evaluation system for vehicle emergency steering auxiliary system
Technical Field
The application relates to the technical field of intelligent driving simulation of vehicles, in particular to a simulation test evaluation method and an evaluation system of an emergency steering auxiliary system of a vehicle.
Background
In the field of intelligent driving, an emergency steering assist system (ESA) is a driving assist system which is enabled under the condition of collision risk, is used for interfering a vehicle steering system and enabling a vehicle to avoid a target with collision risk in front, and is suitable for a scene where an automatic emergency braking system (AEB) is enabled and cannot avoid collision. Generally, the Time To Collision (TTC) at ESA enable time is generally less than the Time To Collision (TTC) at AEB enable time.
Since the working condition when the ESA function is triggered is dangerous (the TTC value is small), in the actual vehicle test stage, even if a security officer is on the vehicle, the safety of the vehicle and the surroundings cannot be ensured. In particular, the phenomenon of understeer, oversteer and even out of control of the vehicle is easy to occur in the process of enabling. It is therefore crucial how to fully and safely test ESA functions during development and testing. Based on this, testing the ESA system through a virtual simulation mode gradually becomes a current research and development trend, and by carrying out massive scene tests on ESA system software in a simulation environment, the decision and steering control capability of a planning control algorithm in the ESA can be fully verified. Because an ESA system usually needs simulation evaluation under a plurality of scenes, a plurality of evaluation items are correspondingly arranged under each simulation environment, and the test result is evaluated in a manual mode at present, a set of high-efficiency and accurate quantitative evaluation scheme for the simulation result is not formed, so that the ESA simulation evaluation period is long, and the evaluation process is not quantitative and irregular due to different experiences of different technicians, so that the confidence coefficient of the evaluation result is influenced; and further, the test period of subsequent real vehicle test verification and calibration is prolonged, and additional development and test cost is generated.
Disclosure of Invention
The invention provides a simulation test evaluation method and an evaluation system of a vehicle emergency steering auxiliary system, which aim to solve or partially solve the technical problems that the simulation evaluation period of the vehicle emergency steering auxiliary system is long, the efficiency is low, the evaluation process is not quantitative and standard, and the accuracy of the evaluation result is influenced.
In order to solve the technical problem, the invention provides a simulation test evaluation method of a vehicle emergency steering auxiliary system, which comprises the following steps:
determining a simulation test item of the vehicle emergency steering auxiliary system and a target result parameter corresponding to the simulation test item; the simulation test items comprise M first evaluation indexes and N second evaluation indexes, and the target result parameters comprise first target result parameters corresponding to the first evaluation indexes, second target result parameters corresponding to the second evaluation indexes and weight coefficients corresponding to the second evaluation indexes; m is more than or equal to 2 and is an integer, and N is more than or equal to 2 and is an integer;
according to the simulation test items, carrying out simulation test on the vehicle emergency steering auxiliary system to obtain first test result parameters corresponding to M first evaluation indexes and second test result parameters corresponding to N second evaluation indexes;
judging whether all the first test result parameters are qualified or not according to the first target result parameters, and outputting Boolean value scores representing whether the simulation tests pass or not;
when the first test result parameters are all qualified, evaluating the second test result parameters according to the second target result parameters to obtain a single score corresponding to each second evaluation index;
determining a weighted score of the vehicle emergency steering auxiliary system according to the single score and the weight coefficient;
and adjusting the vehicle emergency steering auxiliary system according to at least one of the Boolean value score, the single item score and the weighted score.
Optionally, judging whether all the first test result parameters are qualified according to the first target result parameter specifically includes:
judging whether each first test result parameter is qualified or not according to the first target result parameters, and obtaining the Boolean value q corresponding to each first test result parameteri(ii) a Wherein, if the first test result parameter is qualified, the Boolean value q isi1 is ═ 1; if the first test result parameter is not qualified, the Boolean value qi＝0；
With M Boolean values qiIs a diagonal line element structureEstablishing a diagonal matrix D, calculating a determinant detD of the diagonal matrix, and obtaining a Boolean value score representing whether all simulation test results are qualified;
when the Boolean value score is 1, all the first test result parameters are qualified; when the boolean value score is 0, the first test result parameter does not meet all eligibility.
Optionally, the evaluating the second test result parameter according to the second target result parameter to obtain a single score corresponding to each second evaluation index, and specifically includes:
determining a transfer matrix T for evaluating the second test result parameter according to the second target result parameter;
constructing a row vector X according to the second test result parameter;
obtaining a grading row vector P corresponding to the second evaluation index according to the transposition of the row vector X and the transfer matrix T; wherein, the scoring row vector P comprises single scores P corresponding to the N second evaluation indexesi。
Further, determining a weighted score of the vehicle emergency steering assist system according to the single score and the weight coefficient specifically includes:
constructing a weight diagonal matrix W according to the weight coefficient;
transposed vector P from scored row vectors PTAnd a weight diagonal matrix W, and determining an evaluation matrix E;
and solving the sum of diagonal elements of the evaluation matrix E to obtain a weighted score.
Optionally, according to the simulation test item, a simulation test of the vehicle emergency steering assist system is performed to obtain first test result parameters corresponding to the M first evaluation indexes and second test result parameters corresponding to the N second evaluation indexes, and the method specifically includes:
constructing a test vehicle and a target vehicle in simulation software, and constructing a perception fusion and planning decision control model of the test vehicle according to a vehicle emergency steering auxiliary system;
controlling the test vehicle to drive to a target vehicle at a preset speed;
when the target vehicle is in a first preset distance interval of the test vehicle, detecting whether an emergency steering auxiliary system of the vehicle sends an alarm instruction or not; when the vehicle emergency steering auxiliary system sends an alarm instruction, acquiring a first target distance and a first collision time between a test vehicle and a target vehicle at the alarm moment;
when the target vehicle is in a second preset distance interval of the test vehicle, detecting whether a vehicle emergency steering auxiliary system sends a steering command or not; when the vehicle emergency steering auxiliary system sends a steering instruction, controlling the transverse motion control of a steering model of the test vehicle to switch to a sensing fusion and planning decision control model, and acquiring a second target distance and a second collision time between the test vehicle and a target vehicle at the steering moment;
acquiring steering intervention data in the process of controlling the steering intervention of the steering model of the test vehicle by the perception fusion and planning decision control model;
if the test vehicle collides with the target vehicle in the simulation process, acquiring the transverse displacement and the yaw velocity of the test vehicle at the collision moment;
classifying the steering intervention data, the first target distance, the first collision time, the second target distance, the second collision time, the transverse displacement and the yaw rate of the test vehicle to obtain a first test result parameter and a second test result parameter.
Optionally, the M first evaluation indexes include at least one of the following indexes:
in the simulation test process, whether the state jump of the vehicle emergency steering auxiliary system is normal or not is judged;
whether a test vehicle in the simulation software collides with a target vehicle or not;
whether the vehicle emergency steering auxiliary system gives an alarm normally or not;
in the enabling process of the vehicle emergency steering auxiliary system, testing whether the maximum lateral acceleration of the vehicle is smaller than 0.7g, wherein g is the gravity acceleration;
testing whether the vehicle keeps running in an adjacent lane or an initial lane in the enabling process of the vehicle emergency steering auxiliary system;
after the enabling of the emergency steering auxiliary system of the vehicle is finished, testing whether the vehicle deviates from the current lane after continuously running for a third preset distance;
when a target vehicle which relatively runs exists in the left lane, whether the vehicle changes left is tested;
when the left lane line is a yellow single solid line or a yellow double solid line, whether the lane line crosses the lane boundary or not is judged;
when the vehicle emergency steering auxiliary system enters an enabling area, if a target vehicle approaching at a high speed exists behind the vehicle emergency steering auxiliary system, whether the vehicle emergency steering auxiliary system enables the target vehicle to one side is judged;
when the vehicle emergency steering auxiliary system enters an enabling area, if a low-speed or static target vehicle exists in the front side of the vehicle emergency steering auxiliary system, whether the vehicle emergency steering auxiliary system is enabled to one side of the target vehicle is judged.
Optionally, the N second evaluation indexes include at least one of the following indexes:
testing a first collision time between the vehicle and a target vehicle when the vehicle emergency steering assist system gives an alarm;
testing a first longitudinal distance between the vehicle and a target vehicle when the vehicle emergency steering assist system gives an alarm;
testing a second collision time between the vehicle and the target vehicle when the vehicle emergency steering auxiliary system sends a steering command;
testing a second longitudinal distance between the vehicle and the target vehicle when the vehicle emergency steering auxiliary system sends a steering command;
the method comprises the following steps that a vehicle emergency steering auxiliary system tests the lateral speed of a vehicle in the steering intervention enabling process;
the method comprises the following steps that a vehicle emergency steering auxiliary system tests the lateral acceleration of a vehicle in the steering intervention enabling process;
the method comprises the following steps that a vehicle emergency steering auxiliary system tests the lateral acceleration change rate of a vehicle in the steering intervention enabling process;
the method comprises the following steps that a vehicle emergency steering auxiliary system tests the yaw velocity of a vehicle in the steering intervention enabling process;
testing the maximum displacement of the vehicle;
a minimum lateral distance between the test vehicle and the target vehicle;
and the vehicle emergency steering auxiliary system tests the yaw angle of the vehicle after the steering intervention is enabled.
Based on the same inventive concept of the foregoing embodiment, the present invention further provides a simulation test evaluation system of a vehicle emergency steering assist system, including:
the first determination module is used for determining a simulation test item of the vehicle emergency steering auxiliary system and a target result parameter corresponding to the simulation test item; the simulation test items comprise M first evaluation indexes and N second evaluation indexes, and the target result parameters comprise first target result parameters corresponding to the first evaluation indexes, second target result parameters corresponding to the second evaluation indexes and weight coefficients corresponding to the second evaluation indexes; m is more than or equal to 2 and is an integer, and N is more than or equal to 2 and is an integer;
the simulation module is used for carrying out simulation test on the vehicle emergency steering auxiliary system according to the simulation test items to obtain first test result parameters corresponding to the M first evaluation indexes and second test result parameters corresponding to the N second evaluation indexes;
the judging module is used for judging whether the first test result parameters are all qualified or not according to the first target result parameters and outputting Boolean value scores representing whether the simulation tests pass or not;
the evaluation module is used for evaluating the second test result parameters according to the second target result parameters when the first test result parameters are all qualified, and obtaining the single scores corresponding to each second evaluation index;
the second determination module is used for determining the weighted score of the vehicle emergency steering auxiliary system according to the single score and the weight coefficient;
and the adjusting module is used for adjusting the vehicle emergency steering auxiliary system according to at least one of the Boolean value score, the single item score and the weighted score.
Based on the same inventive concept of the foregoing embodiment, the present invention further provides a readable storage medium, on which a computer program is stored, where the computer program, when being executed by a processor, implements the steps of any one of the simulation test evaluation methods in the foregoing technical solutions.
Based on the same inventive concept of the foregoing embodiment, the present invention further provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor, and when the processor executes the program, the steps of any one of the simulation test evaluation methods in the foregoing technical solutions are implemented.
Through one or more technical schemes of the invention, the invention has the following beneficial effects or advantages:
the invention provides an evaluation method for an emergency steering auxiliary ESA system simulation test, which comprises the steps of establishing a simulation test evaluation specification by determining a simulation test item of an ESA system, and then obtaining first test result parameters corresponding to M first evaluation indexes and second test result parameters corresponding to N second evaluation indexes when carrying out the simulation test of the ESA system; the M first evaluation indexes are must-reach indexes, whether all first test result parameters corresponding to the must-reach indexes are qualified is judged, a Boolean value score representing whether the simulation test passes or not is output, and the judgment is used for determining whether the must-reach function is normally enabled or not; if all the first test result parameters are qualified, the simulation is passed, then the performance evaluation indexes, namely the second test result parameters corresponding to the N second evaluation indexes are scored to obtain the single score corresponding to each second evaluation index, and then all the single scores are weighted according to the weight coefficients to obtain weighted scores; the single-item score is used for evaluating each performance dimension of the virtual vehicle model for implementing emergency steering in the ESA enabling process, and the weighted score is used for comprehensively evaluating the overall control capacity of the virtual vehicle model for implementing emergency steering in the ESA enabling process; through the Boolean value scoring, the single item scoring and the weighted scoring, whether the performance of the ESA achieves the system design target or not can be judged, and a corresponding optimization suggestion is provided according to the scoring, so that the quick iterative verification can be realized in the whole process of function development, and a guidance suggestion is provided for parameter calibration; in general, the method establishes an efficient simulation test quantitative evaluation mechanism of the ESA system, can perform rapid test according to different simulation scenes during function development, and obtains a more accurate quantitative evaluation result so as to find out a functional algorithm logic problem as early as possible; the method can also be used for system verification test at the later development stage so as to confirm whether the design target is achieved; meanwhile, the test scene with high coverage can perform comprehensive function and performance investigation on the functions in the simulation environment, and assist in performing preliminary calibration, so that the test period of real vehicle test verification and calibration can be greatly shortened, and the development and test cost is reduced.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 illustrates a flow chart of a simulation test evaluation method for a vehicle emergency steering assist system in accordance with one embodiment of the present invention;
FIG. 2 shows a flow diagram of a simulation scenario according to one embodiment of the invention;
FIG. 3 shows a schematic diagram of a simulation test evaluation system of a vehicle emergency steering assist system according to one embodiment of the invention.
Detailed Description
In order to make the present application more clearly understood by those skilled in the art to which the present application pertains, the following detailed description of the present application is made with reference to the accompanying drawings by way of specific embodiments. Throughout the specification, unless otherwise specifically noted, terms used herein should be understood as having meanings as commonly used in the art. Accordingly, unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. If there is a conflict, the present specification will control. Unless otherwise specifically stated, various apparatuses and the like used in the present invention are either commercially available or can be prepared by existing methods.
In order to solve the problems that an existing emergency steering assist system (hereinafter referred to as an ESA system) lacks an efficient and accurate virtual simulation quantitative evaluation scheme, which results in long evaluation period, low efficiency and an irregular and irregular evaluation process, in an optional embodiment, as shown in fig. 1, a simulation test evaluation method for a vehicle emergency steering assist system is provided, and the overall idea is as follows:
s1: determining a simulation test item of the vehicle emergency steering auxiliary system and a target result parameter corresponding to the simulation test item; the simulation test items comprise M first evaluation indexes and N second evaluation indexes, and the target result parameters comprise first target result parameters corresponding to the first evaluation indexes, second target result parameters corresponding to the second evaluation indexes and weight coefficients corresponding to the second evaluation indexes; m is more than or equal to 2 and is an integer, and N is more than or equal to 2 and is an integer;
s2: according to the simulation test items, carrying out simulation test on the vehicle emergency steering auxiliary system to obtain first test result parameters corresponding to M first evaluation indexes and second test result parameters corresponding to N second evaluation indexes;
s3: judging whether all the first test result parameters are qualified or not according to the first target result parameters, and outputting Boolean value scores representing whether the simulation tests pass or not;
s4: when the first test result parameters are all qualified, evaluating the second test result parameters according to the second target result parameters to obtain a single score corresponding to each second evaluation index;
s5: determining a weighted score of the vehicle emergency steering auxiliary system according to the single score and the weight coefficient;
s6: and adjusting the vehicle emergency steering auxiliary system according to at least one of the Boolean value score, the single item score and the weighted score.
Specifically, to perform a simulation test on a certain ESA system, a virtual simulation scenario needs to be constructed according to test requirements, and a simulation test item that needs to be evaluated on the ESA system when performing virtual simulation in the virtual simulation scenario is determined. The virtual simulation scene is constructed based on developed test cases, when the simulation scene is constructed, a simulation test engineer can complete development and integration of the test cases based on standard laws and regulations, function definition documents and brainstorms to form laws and regulations test, state conversion, typical scenes, special/dangerous scenes and functional safety/fault diagnosis test cases, the test cases are strongly related to an ESA system and must meet all test requirements of the ESA system, then the simulation scene can be constructed in simulation software (for example, Carmaker software) according to the test cases, and first test result parameters corresponding to first evaluation indexes and second test result parameters corresponding to N second evaluation indexes are output through simulation test in the simulation scene.
Optionally, a simulation test of the vehicle emergency steering assist system is performed according to a simulation test item, and alternatives for obtaining first test result parameters corresponding to M first evaluation indexes and second test result parameters corresponding to N second evaluation indexes are as follows:
constructing a test vehicle and a target vehicle in simulation software, and constructing a perception fusion and planning decision control model of the test vehicle according to a vehicle emergency steering auxiliary system;
controlling the test vehicle to drive to a target vehicle at a preset speed;
when the target vehicle is in a first preset distance interval of the test vehicle, detecting whether an emergency steering auxiliary system of the vehicle sends an alarm instruction or not; when the vehicle emergency steering auxiliary system sends an alarm instruction, acquiring a first target distance and a first collision time between a test vehicle and a target vehicle at the alarm moment;
when the target vehicle is in a second preset distance interval of the test vehicle, detecting whether a vehicle emergency steering auxiliary system sends a steering command or not; when the vehicle emergency steering auxiliary system sends a steering instruction, controlling the transverse motion control of a steering model of the test vehicle to switch to a sensing fusion and planning decision control model, and acquiring a second target distance and a second collision time between the test vehicle and a target vehicle at the steering moment;
acquiring steering intervention data in the process of controlling the steering intervention of the steering model of the test vehicle by the perception fusion and planning decision control model;
if the test vehicle collides with the target vehicle in the simulation process, acquiring the transverse displacement and the yaw velocity of the test vehicle at the collision moment;
classifying the steering intervention data, the first target distance, the first collision time, the second target distance, the second collision time, the transverse displacement and the yaw rate of the test vehicle to obtain a first test result parameter and a second test result parameter.
Specifically, reference may be made to a flow example of a simulation scenario constructed based on a certain ESA test requirement and a functional specification, shown in fig. 2: firstly, simulating the whole vehicle environment to carry out power-on initialization operation, monitoring the state bit of the ESA system after the power-on is finished, and detecting whether the state of the ESA system enters an available state (the available state represents that the system is initialized normally, but the function is not started yet). The simulation then completes the ESA function activation operation during which the longitudinal and lateral movements of the test vehicle are controlled by the driver model in the simulation software. After the function starting operation is completed, whether the state of the ESA enters an authorized state or not is monitored (the authorization indicates that the ESA function is normally started but is not enabled yet), and at the moment, the driver model continuously controls the test vehicle to drive forwards at a constant speed to approach a target vehicle in front. When the distance between the two vehicles approaches, if the system gives an alarm, recording the distance between the alarm time and the target vehicle and the alarm time TTC; if the system sends a steering control instruction, the transverse motion control of the test vehicle is immediately switched to a planning decision control model, and the distance between the test vehicle and the target vehicle and the TTC are output; and if the system does not send any response and the front target vehicle collides, the recorded test data simulation is terminated. After the ESA system sends a steering command, the steering model of the test vehicle executes steering intervention control (ESA enabling), and in the whole process of the ESA enabling, EPS (electronic power steering system) control torque request value, EPS torque response value, test vehicle speed, yaw angular velocity, lateral displacement, lateral velocity, lateral acceleration, distance (horizontal and longitudinal) between the test vehicle and a target vehicle and the like sent by the ESA are continuously recorded until the steering intervention is terminated or collision occurs. If the collision happens, recording the bright transverse displacement of the test vehicle at the collision moment, and outputting the yaw velocity of the test vehicle at the collision moment; if no collision occurs, recording the test data after ESA is enabled to be terminated, and ending the simulation test.
In this embodiment, according to the simulation test item, the simulation test item includes a plurality of first evaluation indexes and second evaluation indexes, and a first target result parameter and a second target result parameter corresponding to all the evaluation indexes are made, where the first target result parameter and the second target result parameter are target results that need to be achieved by the test case. Then, in the simulation evaluation process of the ESA, collecting test result data corresponding to the simulation test items, namely a first test result parameter and a second test result parameter in the scheme, then determining a grading rule according to a preset target result parameter, automatically evaluating the test result parameters obtained by simulation through secondary development to obtain the evaluation/grading results of the actual measurement data corresponding to all the simulation test items, and adjusting a functional algorithm, logic and the like in the ESA system according to the evaluation results.
In this embodiment, the first evaluation index is a must-reach index item that is required to pass when the ESA system is simulated, that is, the work performance of the ESA system must be satisfied, if one of the first test result parameters corresponding to the M first evaluation indexes fails, it is indicated that the work performance does not reach the design target, it is determined that the simulation test of the ESA system in the current simulation scenario does not pass, and the system planning decision control model and (or) the calibration quantity may be adjusted and then the test is performed again; the second evaluation index is a performance evaluation index of the ESA system and is used for reflecting the good degree of the work performance of the ESA system, corresponding second test result parameters can be subjected to single scoring according to second target result parameters, and then all the single scoring is calculated according to the weight coefficient to obtain the weighted scoring of the whole ESA system and is used for reflecting the overall performance of the ESA system.
Optionally, the M first evaluation indexes include at least one of the following indexes:
in the simulation test process, whether the state jump of the vehicle emergency steering auxiliary system is normal or not is judged;
whether a test vehicle in the simulation software collides with a target vehicle or not;
whether the vehicle emergency steering auxiliary system gives an alarm normally or not;
in the enabling process of the vehicle emergency steering auxiliary system, testing whether the maximum lateral acceleration of the vehicle is smaller than 0.7g, wherein g is the gravity acceleration;
after the enabling process of the vehicle emergency steering auxiliary system, testing whether the vehicle keeps running in an adjacent lane or an initial lane;
after the enabling of the emergency steering auxiliary system of the vehicle is finished, testing whether the vehicle deviates from the current lane after continuously running for a third preset distance;
when a target vehicle which relatively runs exists in the left lane, whether the vehicle changes left is tested;
when the left lane line is a yellow single solid line or a yellow double solid line, whether the lane line crosses the lane boundary or not is judged;
when the vehicle emergency steering auxiliary system enters an enabling area, if a target vehicle approaching at a high speed exists behind the vehicle emergency steering auxiliary system, whether the vehicle emergency steering auxiliary system enables the target vehicle to one side is judged;
when the vehicle emergency steering auxiliary system enters an enabling area, if a low-speed or static target vehicle exists in the front side of the vehicle emergency steering auxiliary system, whether the vehicle emergency steering auxiliary system is enabled to one side of the target vehicle is judged.
Optionally, the N second evaluation indexes include at least one of the following indexes:
testing a first collision time between the vehicle and a target vehicle when the vehicle emergency steering assist system gives an alarm;
testing a first longitudinal distance between the vehicle and a target vehicle when the vehicle emergency steering assist system gives an alarm;
testing a second collision time between the vehicle and the target vehicle when the vehicle emergency steering auxiliary system sends a steering command;
testing a second longitudinal distance between the vehicle and the target vehicle when the vehicle emergency steering auxiliary system sends a steering command;
the method comprises the following steps that a vehicle emergency steering auxiliary system tests the lateral speed of a vehicle in the steering intervention enabling process;
the method comprises the following steps that a vehicle emergency steering auxiliary system tests the lateral acceleration of a vehicle in the steering intervention enabling process;
the method comprises the following steps that a vehicle emergency steering auxiliary system tests the lateral acceleration change rate of a vehicle in the steering intervention enabling process;
the method comprises the following steps that a vehicle emergency steering auxiliary system tests the yaw velocity of a vehicle in the steering intervention enabling process;
testing the maximum displacement of the vehicle;
a minimum lateral distance between the test vehicle and the target vehicle;
and the vehicle emergency steering auxiliary system tests the yaw angle of the vehicle after the steering intervention is enabled.
When different simulation scenes or different requirements are met, the first evaluation index and the second evaluation index can be combined or flexibly adjusted.
The embodiment provides an evaluation method for an emergency steering auxiliary ESA system simulation test, which comprises the steps of establishing a simulation test evaluation specification by determining a simulation test item of an ESA system, and then obtaining first test result parameters corresponding to M first evaluation indexes and second test result parameters corresponding to N second evaluation indexes when carrying out the simulation test of the ESA system; the M first evaluation indexes are must-reach indexes, whether all first test result parameters corresponding to the must-reach indexes are qualified is judged, a Boolean value score representing whether the simulation test passes or not is output, and the judgment is used for determining whether the must-reach function is normally enabled or not; if all the first test result parameters are qualified, the simulation is passed, then the performance evaluation indexes, namely the second test result parameters corresponding to the N second evaluation indexes are scored to obtain the single score corresponding to each second evaluation index, and then all the single scores are weighted according to the weight coefficients to obtain weighted scores; the single-item score is used for evaluating each performance dimension of the virtual vehicle model for implementing emergency steering in the ESA enabling process, and the weighted score is used for comprehensively evaluating the overall control capacity of the virtual vehicle model for implementing emergency steering in the ESA enabling process; through the Boolean value scoring, the single item scoring and the weighted scoring, whether the performance of the ESA achieves the system design target or not can be judged, and a corresponding optimization suggestion is provided according to the scoring, so that the quick iterative verification can be realized in the whole process of function development, and a guidance suggestion is provided for parameter calibration; in general, the method establishes an efficient simulation test quantitative evaluation mechanism of the ESA system, can perform rapid test according to different simulation scenes during function development, and obtains a more accurate quantitative evaluation result so as to find out a functional algorithm logic problem as early as possible; the method can also be used for system verification test at the later development stage so as to confirm whether the design target is achieved; meanwhile, the test scene with high coverage can perform comprehensive function and performance investigation on the functions in the simulation environment, and assist in performing preliminary calibration, so that the test period of real vehicle test verification and calibration can be greatly shortened, and the development and test cost is reduced.
Based on the same inventive concept of the previous embodiment, in the following embodiment, the above scheme is explained in detail:
under a certain simulation scene, a first evaluation index (a must reach index, as shown in table 1) of the ESA system is determined, and the must reach index is obtained according to the functional requirements, the driving safety and the driver behavior analysis of the ESA system.
Table 1: example of ESA first evaluation index
Figure BDA0002832482090000131
Figure BDA0002832482090000141
1)q1The functional state machine for monitoring the ESA throughout the simulation is in an expected state (e.g., waiting, active, inhibited, fault state, etc.).
2)q2The safety index is a necessary index for driving safety, and indicates that an ESA system must ensure that the ESA system does not collide with a front dangerous target or a vehicle-side obstacle target in the emergency steering intervention process.
3)q3The system is based on the reach indexes provided by the ESA function definition and the driver behavior analysis, and the system is indicated to send a pre-collision alarm to the driver in advance before enabling, so that the aim of warning the driver is fulfilled.
4)q4The vehicle lateral acceleration used for restraining the ESA enabling process is a running safety index under an emergency condition, the maximum lateral acceleration value of the vehicle during the ESA enabling process is required to be not more than 0.7g (reference value), otherwise the vehicle can be under-steered or over-steered, and the risk of runaway is increased.
5)q5Based on the ESA function definition and the driver behavior analysis, after the system enabling is required to be finished, the vehicle must travel in the adjacent lane or the initial lane without crossing the line.
6)q6The method is a stable constraint of the vehicle course angle after the ESA is enabled, and after the ESA is enabled, if the road is a straight road and the driver does not perform steering in advance, the vehicle can drive 50m in the current lane (the lane width is 3.75m) without deviating from the lane.
7)q7Based on the function definition of the ESA and the driving safety requirement, when a dangerous target vehicle relatively drives on the left side, the ESA enabling period cannot change the lane to the left side, and only the lane change to the right side is allowed.
8)q8Based on the function definition of the ESA and the driving safety requirement, when the lane line on the left side is a yellow single solid line or a yellow double solid line (i.e. the left side of the lane line is a reverse lane), the ESA enabling process must not cross the lane boundary so as to avoid the collision risk with the oncoming vehicle.
9)q9Based on the function definition of the ESA and the requirement of driving safety, when the ESA enters an enabling area, if a dangerous target vehicle approaching at a high speed exists behind the ESA, the ESA cannot be enabled to one side of the dangerous target vehicle.
10)q10Based on the function definition of the ESA and the requirement of driving safety, when the ESA enters the enabling area, if a dangerous target vehicle with low speed or static is arranged in front of the side, the ESA cannot enable the dangerous target vehicle side.
Q is the aboveiIs a boolean value, q is the first test result parameter corresponding to the first evaluation index corresponding to the first target result parameteriThe value of (1) indicates that the simulation test item passes; if not, qiThe value of (1) is 0, which indicates that the simulation test item does not pass.
Optionally, a diagonal matrix D is introduced to evaluate a first test result parameter of the ESA, which is specifically as follows:
judging whether each first test result parameter is qualified or not according to the first target result parameters, and obtaining the Boolean value q corresponding to each first test result parameteri(ii) a Wherein, if the first test result parameter is qualified, the Boolean value q isi1 is ═ 1; if the first test result parameter is not qualified, the Boolean value qi＝0；
With M Boolean values qiConstructing a diagonal matrix D for diagonal elements, calculating a determinant detD of the diagonal matrix, and obtaining a Boolean value score representing whether all simulation test results are qualified;
when the Boolean value score is 1, all the first test result parameters are qualified; when the boolean value score is 0, the first test result parameter does not meet all eligibility.
Specifically, the diagonal matrix D is represented by formula (1):
D＝diag(q1，q2，q3，q4，q5，q6，q7，q8，q9，q10...) (1)
if and only if qi(i ═ 1,2,3,4,5,6,7,8,9,10, …) all are 1, that is, when all the requisite indices of ESA function are satisfied, det (d) ═ 11, if there is a must-meet criterion, i.e. qiIf one or more of (i ═ 1,2,3,4,5,6,7,8,9,10, …) is 0, det (d) is 0.
The test Result of the must index is counted as R1(Result1), and the calculation method of the must index is shown as a formula (2):
R1＝det(D) (2)
in the present simulation scenario, the second evaluation index, that is, the evaluation index of the ESA system performance, is as shown in table 2:
table 2 second evaluation index example
Figure BDA0002832482090000151
Figure BDA0002832482090000161
1)TTCwarningThe system is used for calculating the pre-collision alarm time sent by the ESA system and evaluating whether the alarm time is too early or too late;
2)dwarningthe distance between the test vehicle and the front target vehicle is calculated when the ESA system gives an alarm, and whether the alarm distance is too long or too short is evaluated;
3)TTCsteeringthe system is used for calculating and evaluating the time TTC of collision with a target vehicle when the ESA system enables emergency steering, which is a specific performance index of the ESA system;
4)dsteeringfor calculating and evaluating the distance to the target vehicle when the ESA system enables emergency steering, which is a characteristic performance index of the ESA system
5)vyThe device is used for calculating the lateral speed of the test vehicle in the whole simulation period, evaluating the absolute value of the lateral speed, and presetting a target lateral speed;
6)ayfor calculating the lateral acceleration of the test vehicle during the entire simulation, this value must generally not be less than 3m/s2(reference value), otherwise, identify the ESA mediumEarly entry, the ESA system has specific requirements for this value, which usually must not exceed 7m/s2(reference value), otherwise the vehicle is at risk of being out of control;
7)
Figure BDA0002832482090000162
for calculating the lateral acceleration rate of the test vehicle during the whole simulation, the ESA system has specific requirements for the value, and usually the value must not exceed 10m/s ^3 (reference value), otherwise the vehicle has the risk of being out of control;
8)Yawratefor calculating the yaw rate of the test vehicle during the entire simulation;
9)LatDisplacemaxthe method is used for calculating the transverse maximum displacement of a test vehicle during the ESA enabling period, an ESA system has specific requirements for the numerical value, when the ESA enables the vehicle to change lanes, the transverse displacement of the test vehicle is defined to be 3.5 m-3.75 m according to functions, the deviation of the transverse displacement of the vehicle is calculated by taking the data as a reference, and the deviation is used for evaluating whether the transverse displacement is larger or smaller and calculating the size of the deviation;
10)LatDistanceTarminbased on the function definition of the ESA and the requirement of driving safety, when the ESA enters an enabling area, if a dangerous target vehicle approaching at a high speed exists behind the ESA, the ESA cannot be enabled to one side of the dangerous target vehicle;
11)Yawterminatefor calculating the course angle (relative to the lane path direction) of the ESA enabled end time (test vehicle), which is a performance indicator of interest to the ESA function.
In order to quickly implement the evaluation of the second test result parameter corresponding to the second evaluation index, optionally, the evaluation of the second test result parameter is performed according to the second target result parameter to obtain a single score corresponding to each second evaluation index, and specifically includes:
determining a transfer matrix T for evaluating the second test result parameter according to the second target result parameter;
constructing a row vector X according to the second test result parameter;
obtaining a second evaluation index according to the transposition of the row vector X and the transfer matrix TMarking a corresponding scoring row vector P; wherein, the scoring row vector P comprises single scores P corresponding to the N second evaluation indexesi。
Further, determining a weighted score of the vehicle emergency steering assist system according to the single score and the weight coefficient specifically includes:
constructing a weight diagonal matrix W according to the weight coefficient;
transposed vector P from scored row vectors PTAnd a weight diagonal matrix W, and determining an evaluation matrix E;
and solving the sum of diagonal elements of the evaluation matrix E to obtain a weighted score.
Specifically, all the second test result parameters are written into the row vector X as follows:
Figure BDA0002832482090000171
and according to the simulation test data of each scene, scoring according to the scoring rules aiming at each evaluation standard, wherein the full score is 5. The factors influencing the scoring result are mainly determined from the following aspects
1) And (4) defining system functions. According to the function definition of the system, if the function definition has a clear performance index interval range, reference can be cited;
2) and (4) driving safety. The driving safety mainly aims at dynamic parameters such as speed, acceleration and acceleration rate of the vehicle, and different grading standards are set by combining different functional scenes on the basis of vehicle dynamics limitation requirements;
3) the driver behavior. According to the inertial thinking of daily driving of a driver, parameters such as alarm timing, intervention timing and the like are evaluated, the enabling timing of the system is required to be not too early or too late, and if the relative error between the enabling timing and the function requirement setting is less than 5%, the system can be rated as 5.
Take the time to collision TTC between the first performance evaluation index warning time and the target vehicle as an example. The TTC value is equal to the relative distance between the test vehicle and the target vehicle divided by the relative velocity of the test vehicle and the target vehicleWhen the representation of the ESA function is not mediated, how long the vehicle and the target vehicle still collide with each other. The alarm time and the target TTC represent the time when the ESA system sends out the alarm, and how long the test vehicle collides with the target vehicle. Usually, the value cannot be small (i.e. the alarm is too late and does not serve the purpose of warning the driver) or large (frequent alarms are generated in daily driving, and the driver complains are caused). For example, if the TTC obtained from the simulation test result is obtainedwarningAt 2.7s, the score was 4. Alarm time and Target TTC (TTC)warning) The specific scoring rules are shown in table 3:
table 3: alarm time and target vehicle TTC (TTC)warning) Specific scoring rules example
Figure BDA0002832482090000181
The evaluation index score table of the ESA performance evaluation index obtained by scoring each second evaluation index is shown in 4:
table 4: ESA Performance evaluation index score expression example
Figure BDA0002832482090000191
Remarking: when each simulation scene is constructed, a group of performance index theoretical data aiming at the scene and based on factors such as functional requirements and driving safety is provided, actual data (second test result parameters) obtained from simulation test results are compared with theoretical data (second target result parameters) to calculate relative errors or deviation, and then the calculation results of the relative errors or deviation are used as scoring basis of the performance indexes in the scene.
In specific implementation, a scoring result vector of the performance evaluation index is defined as P (performance), and each element P of P is P1，p2，p3… represents the score of the corresponding performance evaluation index, and the scoring result vector is shown in formula (4):
P＝(p1，p2，p3，p4，p5，p6，p7，p8，p9，p10，p11) (4)
according to the scoring rules in table 4, a transfer matrix T is constructed so that the scoring result vector satisfies the relationship shown in equation (5):
P＝XTT (5)
the transfer matrix T is determined according to scoring rules under different simulation scenes or according to target results of test cases.
The weights are calculated for the performance index scores to obtain the evaluation score of the ESA system performance in a certain simulation scene. According to the ESA function definition, the driving safety, the dimensionality of the driver behavior analysis and the like, and the result analysis of the early-stage function simulation data, the performance index weight coefficient of the ESA system is comprehensively obtained, and the first and second important performance evaluation indexes of the ESA system are as follows,
the steering intervention time and the target TTC are important indexes for judging whether the system enabling time is proper or not, a higher weight value is usually given, the optional range is 15-25%, and the preferred value is 20%;
the minimum lateral distance from the target is used to judge whether the minimum displacement of the system lateral control meets the expectation to avoid collision, and usually gives a next highest weight, with an optional range of 10-20%, and a preferred value of 15%.
Then, further obtaining a weight coefficient corresponding to each performance evaluation parameter (second evaluation index): omega. ofi(∑ωi＝1，ωi>0；i＝1,2,3,4,5,6,7,8,9,10,11,…)。
Setting the evaluation result of an ESA system in a certain simulation scene as R (result), introducing a main diagonal weight matrix W (weight matrix) to represent the weight of each performance index, and introducing an evaluation matrix E (evaluation) to represent a performance index evaluation result matrix, wherein the main diagonal weight matrix is shown as a formula (6):
W＝diag(ω1，ω2，…，ω11，…)；E＝PTW (6)；
then, in summary:
Figure BDA0002832482090000201
as can be seen from the above formula, if there is a hit indicator that is not met, i.e., R1 is 0, then the evaluation result R is 0, indicating that the test failed; if the must-answer indexes are all satisfied, an evaluation result R can be calculated through evaluation results of 11 performance indexes recorded in the simulation process, and the value of R is the performance evaluation score of the ESA system in a certain simulation scene. If the R value is lower than zero, the ESA system meets the required index, but the performance evaluation score is lower. Performance indicators that result in lower R values, such as steering intervention time and target TTC, may be analyzed. If the index has a large negative error, the intervention enabling time of the ESA system is too late, a large collision risk exists in the real vehicle environment, and a driver feels great discomfort. The calculation module for judging the collision risk of the adjustable ESA system or the related calibration quantity is modified, so that the enabling intervention time of the ESA system is advanced. And after the modification is finished, performing regression testing in the same scene, obtaining a new evaluation result Rnew, comparing the Rnew with the R, verifying whether the modification is effective, and simultaneously determining the influence of the modification on other performance evaluation indexes so as to achieve the aim of generally improving the R value.
In general, by vectorizing a first test result parameter (must reach an index item) and a second test result parameter (performance evaluation item), then matrixing evaluation methods corresponding to a weight coefficient, a first target result parameter and a second target result parameter, and by matrix operation, simulation result data obtained under a current simulation scene can be quickly and quantitatively scored, so that subjective uncertainty caused by artificial evaluation is avoided, and the evaluation efficiency is remarkably improved; the scheme is particularly suitable for centrally carrying out the simulation test of the ESA system in a plurality of simulation scenes in a certain time period, and can quickly and efficiently carry out quantitative evaluation on the high-flux simulation test result.
The evaluation methods proposed in the above examples can be used for model-in-loop testing (MiL testing) for ESA function. The main purpose of the MiL test is to implement a model interface test, a perception fusion algorithm test, and a planning decision control algorithm test. The simulation test input is a software interface definition book, a perception fusion and planning decision control model. And analyzing a signal interface of the model according to the software interface definition, connecting a sensor model, a vehicle model, a road model and the like of the simulation software with the sensing module, and connecting the sensing module and the road model according to the signal requirements of the sensing module and the regulation module. The main outputs of the planning decision control model are an accelerator opening, a brake pedal opening and an EPS (electric power steering) corner or torque control instruction, and the output signals are connected with the vehicle power of simulation software to form an MiL (simulation modeling language) simulation environment. During the simulation test, the ESA simulation test scenes need to be called, and the hit indexes and performance index data of each ESA simulation scene are obtained through automatic test execution for subsequent evaluation.
Based on the same inventive concept of the foregoing embodiment, in yet another alternative embodiment, as shown in fig. 3, there is provided a simulation test evaluation system of an emergency steering assist system of a vehicle, the simulation test evaluation system including:
the first determination module 10 is used for determining a simulation test item of the vehicle emergency steering auxiliary system and a target result parameter corresponding to the simulation test item; the simulation test items comprise M first evaluation indexes and N second evaluation indexes, and the target result parameters comprise first target result parameters corresponding to the first evaluation indexes, second target result parameters corresponding to the second evaluation indexes and weight coefficients corresponding to the second evaluation indexes; m is more than or equal to 2 and is an integer, and N is more than or equal to 2 and is an integer;
the simulation module 20 is configured to perform a simulation test on the vehicle emergency steering assist system according to a simulation test project, and obtain first test result parameters corresponding to the M first evaluation indexes and second test result parameters corresponding to the N second evaluation indexes;
the judging module 30 is configured to judge whether all the first test result parameters are qualified according to the first target result parameter, and output a boolean value score representing whether the simulation test passes or not;
the evaluation module 40 is used for evaluating the second test result parameters according to the second target result parameters when all the first test result parameters are qualified, and obtaining the single scores corresponding to each second evaluation index;
the second determination module 50 is used for determining the weighted score of the vehicle emergency steering auxiliary system according to the single score and the weight coefficient;
and an adjusting module 60, configured to adjust the vehicle emergency steering assist system according to at least one of the boolean score, the singles score, and the weighted score.
Optionally, the determining module 30 is specifically configured to:
judging whether each first test result parameter is qualified or not according to the first target result parameter, and obtaining a Boolean value q corresponding to each first test result parameteri(ii) a Wherein, if the first test result parameter is qualified, the Boolean value q isi1 is ═ 1; if the first test result parameter is unqualified, the Boolean value q isi＝0；
With M of said Boolean values qiConstructing a diagonal matrix D for diagonal elements, calculating a determinant detD of the diagonal matrix, and obtaining a Boolean value score representing whether all simulation test results are qualified;
when the Boolean value score is 1, all the first test result parameters are qualified; when the boolean value score is 0, the first test result parameter does not satisfy all eligibility.
Optionally, the evaluation module 40 is specifically configured to:
determining a transfer matrix T for evaluating the second test result parameter according to the second target result parameter;
constructing a row vector X according to the second test result parameter;
obtaining a scoring row vector P corresponding to the second evaluation index according to the transpose of the row vector X and the transfer matrix T; wherein the scoring row vector P comprises single scores P corresponding to the N second evaluation indexesi。
Optionally, the second determining module 50 is specifically configured to:
constructing a weight diagonal matrix W according to the weight coefficient;
transpose vector P from the scoring row vector PTAnd the weight diagonal matrix W, determining an evaluation matrix E;
and solving the sum of diagonal elements of the evaluation matrix E to obtain the weighted score.
Based on the same inventive concept of the foregoing embodiments, in yet another alternative embodiment, a readable storage medium is provided, on which a computer program is stored, which when executed by a processor implements the steps of the simulation test evaluation method in the foregoing embodiments.
Based on the same inventive concept of the foregoing embodiments, in yet another alternative embodiment, an electronic device is provided, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the computer program, the steps of the simulation test evaluation method in the foregoing embodiments are implemented.
Through one or more embodiments of the present invention, the present invention has the following advantageous effects or advantages:
the invention provides an evaluation method for an emergency steering auxiliary ESA system simulation test, which comprises the steps of establishing a simulation test evaluation specification by determining a simulation test item of an ESA system, and then obtaining first test result parameters corresponding to M first evaluation indexes and second test result parameters corresponding to N second evaluation indexes when carrying out the simulation test of the ESA system; the M first evaluation indexes are must-reach indexes, whether all first test result parameters corresponding to the must-reach indexes are qualified is judged, a Boolean value score representing whether the simulation test passes or not is output, and the judgment is used for determining whether the must-reach function is normally enabled or not; if all the first test result parameters are qualified, the simulation is passed, then the performance evaluation indexes, namely the second test result parameters corresponding to the N second evaluation indexes are scored to obtain the single score corresponding to each second evaluation index, and then all the single scores are weighted according to the weight coefficients to obtain weighted scores; the single-item score is used for evaluating each performance dimension of the virtual vehicle model for implementing emergency steering in the ESA enabling process, and the weighted score is used for comprehensively evaluating the overall control capacity of the virtual vehicle model for implementing emergency steering in the ESA enabling process; through the Boolean value scoring, the single item scoring and the weighted scoring, whether the performance of the ESA achieves the system design target or not can be judged, and a corresponding optimization suggestion is provided according to the scoring, so that the quick iterative verification can be realized in the whole process of function development, and a guidance suggestion is provided for parameter calibration; in general, the method establishes an efficient simulation test quantitative evaluation mechanism of the ESA system, can perform rapid test according to different simulation scenes during function development, and obtains a more accurate quantitative evaluation result so as to find out a functional algorithm logic problem as early as possible; the method can also be used for system verification test at the later development stage so as to confirm whether the design target is achieved; meanwhile, the test scene with high coverage can perform comprehensive function and performance investigation on the functions in the simulation environment, and assist in performing preliminary calibration, so that the test period of real vehicle test verification and calibration can be greatly shortened, and the development and test cost is reduced.
While the preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all alterations and modifications as fall within the scope of the application.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.

Claims (10)

1. A simulation test evaluation method for an emergency steering assist system of a vehicle is characterized by comprising the following steps:
determining a simulation test item of the vehicle emergency steering auxiliary system and a target result parameter corresponding to the simulation test item; the simulation test items comprise M first evaluation indexes and N second evaluation indexes, and the target result parameters comprise first target result parameters corresponding to the first evaluation indexes, second target result parameters corresponding to the second evaluation indexes and weight coefficients corresponding to the second evaluation indexes; m is more than or equal to 2 and is an integer, and N is more than or equal to 2 and is an integer;
according to the simulation test items, performing simulation test on the vehicle emergency steering auxiliary system to obtain first test result parameters corresponding to the M first evaluation indexes and second test result parameters corresponding to the N second evaluation indexes;
judging whether all the first test result parameters are qualified or not according to the first target result parameters, and outputting Boolean value scores representing whether the simulation tests pass or not;
when all the first test result parameters are qualified, evaluating the second test result parameters according to the second target result parameters to obtain a single score corresponding to each second evaluation index;
determining a weighted score of the vehicle emergency steering assist system according to the single score and the weight coefficient;
adjusting the vehicle emergency steering assist system according to at least one of the Boolean score, the singles score, and the weighted score.
2. The method for evaluating a simulation test according to claim 1, wherein the determining whether all of the first test result parameters are qualified according to the first target result parameter specifically comprises:
judging whether each first test result parameter is qualified or not according to the first target result parameter, and obtaining a Boolean value q corresponding to each first test result parameteri(ii) a Wherein, if the first test result parameter is qualified, the Boolean value q isi1 is ═ 1; if the first test result parameter is unqualified, the Boolean value q isi＝0；
With M of said Boolean values qiConstructing a diagonal matrix D for diagonal elements, calculating rows and columns of the diagonal matrixObtaining a Boolean value score representing whether the simulation test result is all qualified or not according to a formula detD;
when the Boolean value score is 1, all the first test result parameters are qualified; when the boolean value score is 0, the first test result parameter does not satisfy all eligibility.
3. The method according to claim 1, wherein the evaluating the second test result parameters according to the second target result parameters to obtain a single score corresponding to each second evaluation index specifically comprises:
determining a transfer matrix T for evaluating the second test result parameter according to the second target result parameter;
constructing a row vector X according to the second test result parameter;
obtaining a scoring row vector P corresponding to the second evaluation index according to the transpose of the row vector X and the transfer matrix T; wherein the scoring row vector P comprises single scores P corresponding to the N second evaluation indexesi。
4. The simulation test evaluation method according to claim 3, wherein the determining a weighted score of the vehicle emergency steering assist system according to the single score and the weight coefficient specifically comprises:
constructing a weight diagonal matrix W according to the weight coefficient;
transpose vector P from the scoring row vector PTAnd the weight diagonal matrix W, determining an evaluation matrix E;
and solving the sum of diagonal elements of the evaluation matrix E to obtain the weighted score.
5. The simulation test evaluation method according to claim 1, wherein the performing a simulation test of the vehicle emergency steering assist system according to the simulation test item to obtain first test result parameters corresponding to the M first evaluation indexes and second test result parameters corresponding to the N second evaluation indexes specifically includes:
building a test vehicle and a target vehicle in simulation software, and building a perception fusion and planning decision control model of the test vehicle according to the vehicle emergency steering auxiliary system;
controlling the test vehicle to drive to the target vehicle at a preset speed;
when the target vehicle is in a first preset distance interval of the test vehicle, detecting whether the vehicle emergency steering auxiliary system sends an alarm instruction; when the vehicle emergency steering auxiliary system sends the alarm instruction, acquiring a first target distance and a first collision time between the test vehicle and the target vehicle at the alarm moment;
when the target vehicle is in a second preset distance interval of the test vehicle, detecting whether the vehicle emergency steering auxiliary system sends a steering command; when the vehicle emergency steering auxiliary system sends the steering instruction, controlling the transverse motion control of a steering model of the test vehicle to be switched to the perception fusion and planning decision control model, and acquiring a second target distance and a second collision time between the test vehicle and the target vehicle at the steering moment;
acquiring steering intervention data in the process that the perception fusion and planning decision control model carries out steering intervention control on the steering model of the test vehicle;
if the test vehicle collides with the target vehicle in the simulation process, acquiring the transverse displacement and the yaw angular velocity of the test vehicle at the collision moment;
classifying the steering intervention data, the first target distance, the first time to collision, the second target distance, the second time to collision, the lateral displacement and the yaw rate of the test vehicle to obtain the first test result parameter and the second test result parameter.
6. The simulation test evaluation method of claim 1, wherein the M first evaluation indexes include at least one of:
in the simulation test process, whether the state jump of the vehicle emergency steering auxiliary system is normal or not is judged;
whether a test vehicle in the simulation software collides with a target vehicle or not;
whether the vehicle emergency steering auxiliary system gives an alarm normally or not;
in the enabling process of the vehicle emergency steering auxiliary system, testing whether the maximum lateral acceleration of the vehicle is smaller than 0.7g, wherein g is gravity acceleration;
testing whether the vehicle keeps running in an adjacent lane or an initial lane during the enabling process of the vehicle emergency steering auxiliary system;
after the enabling of the vehicle emergency steering auxiliary system is finished, testing whether the vehicle deviates from the current lane after continuously running for a third preset distance;
when a target vehicle which relatively runs exists in the left lane, testing whether the vehicle is towards the left;
when the left lane line is a yellow single solid line or a yellow double solid line, whether the lane line crosses the lane boundary or not is judged;
when the vehicle emergency steering auxiliary system enters an enabling area, if a target vehicle approaching at a high speed exists behind the vehicle emergency steering auxiliary system, whether the vehicle emergency steering auxiliary system is enabled to one side of the target vehicle is judged;
when the vehicle emergency steering auxiliary system enters an enabling area, if a low-speed or static target vehicle exists in front of the side, the vehicle emergency steering auxiliary system is enabled to the side of the target vehicle.
7. The simulation test evaluation method of claim 1, wherein the N second evaluation indexes include at least one of:
testing a first collision time between a vehicle and a target vehicle when the vehicle emergency steering assist system issues an alarm;
testing a first longitudinal distance between a vehicle and a target vehicle when the vehicle emergency steering assist system issues an alarm;
testing a second collision time between the vehicle and the target vehicle when the vehicle emergency steering auxiliary system sends a steering command;
testing a second longitudinal distance between the vehicle and the target vehicle when the vehicle emergency steering auxiliary system sends a steering command;
the vehicle emergency steering auxiliary system tests the lateral speed of the vehicle in the steering intervention enabling process;
the vehicle emergency steering auxiliary system tests the lateral acceleration of the vehicle in the steering intervention enabling process;
the vehicle emergency steering auxiliary system tests the lateral acceleration change rate of the vehicle in the steering intervention enabling process;
the vehicle emergency steering auxiliary system tests the yaw velocity of the vehicle in the steering intervention enabling process;
testing the maximum displacement of the vehicle;
a minimum lateral distance between the test vehicle and the target vehicle;
and the vehicle emergency steering auxiliary system tests the yaw angle of the vehicle after the steering intervention enabling is finished.
8. A simulation test evaluation system of an emergency steering assist system for a vehicle, characterized by comprising:
the first determination module is used for determining a simulation test item of the vehicle emergency steering auxiliary system and a target result parameter corresponding to the simulation test item; the simulation test items comprise M first evaluation indexes and N second evaluation indexes, and the target result parameters comprise first target result parameters corresponding to the first evaluation indexes, second target result parameters corresponding to the second evaluation indexes and weight coefficients corresponding to the second evaluation indexes; m is more than or equal to 2 and is an integer, and N is more than or equal to 2 and is an integer;
the simulation module is used for carrying out simulation test on the vehicle emergency steering auxiliary system according to the simulation test items to obtain first test result parameters corresponding to the M first evaluation indexes and second test result parameters corresponding to the N second evaluation indexes;
the judging module is used for judging whether all the first test result parameters are qualified or not according to the first target result parameters and outputting Boolean value scores representing whether the simulation tests pass or not;
the evaluation module is used for evaluating the second test result parameters according to the second target result parameters when all the first test result parameters are qualified, and obtaining a single score corresponding to each second evaluation index;
the second determination module is used for determining a weighted score of the vehicle emergency steering auxiliary system according to the single score and the weight coefficient;
and the adjusting module is used for adjusting the vehicle emergency steering auxiliary system according to at least one of the Boolean value score, the single item score and the weighted score.
9. A readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the simulation test evaluation method of any one of claims 1 to 7.
10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the steps of the simulation test evaluation method of any one of claims 1 to 7 are implemented when the program is executed by the processor.
CN202011464279.0A 2020-12-11 2020-12-11 Simulation test evaluation method and system for vehicle emergency steering auxiliary system Active CN112580201B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011464279.0A CN112580201B (en) 2020-12-11 2020-12-11 Simulation test evaluation method and system for vehicle emergency steering auxiliary system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011464279.0A CN112580201B (en) 2020-12-11 2020-12-11 Simulation test evaluation method and system for vehicle emergency steering auxiliary system

Publications (2)

Publication Number Publication Date
CN112580201A true CN112580201A (en) 2021-03-30
CN112580201B CN112580201B (en) 2022-11-08

Family

ID=75131803

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011464279.0A Active CN112580201B (en) 2020-12-11 2020-12-11 Simulation test evaluation method and system for vehicle emergency steering auxiliary system

Country Status (1)

Country Link
CN (1) CN112580201B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114138634A (en) * 2021-11-15 2022-03-04 苏州浪潮智能科技有限公司 Test case selection method and device, computer equipment and storage medium

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2883798A1 (en) * 2013-12-12 2015-06-17 Airbus DS GmbH Method for computing self-contamination processes of a spacecraft
CN105808857A (en) * 2016-03-10 2016-07-27 清华大学 Prediction method of automobile active safety system effectiveness on the basis of collision deformation depth
WO2020046205A1 (en) * 2018-08-30 2020-03-05 Astropreneurs Hub Pte. Ltd. System and method for simulating a network of one or more vehicles
US20200086856A1 (en) * 2018-09-18 2020-03-19 Hyundai Motor Company Method for escape steering control using system cooperation and vehicle thereof

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2883798A1 (en) * 2013-12-12 2015-06-17 Airbus DS GmbH Method for computing self-contamination processes of a spacecraft
CN105808857A (en) * 2016-03-10 2016-07-27 清华大学 Prediction method of automobile active safety system effectiveness on the basis of collision deformation depth
WO2020046205A1 (en) * 2018-08-30 2020-03-05 Astropreneurs Hub Pte. Ltd. System and method for simulating a network of one or more vehicles
US20200086856A1 (en) * 2018-09-18 2020-03-19 Hyundai Motor Company Method for escape steering control using system cooperation and vehicle thereof

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
MARTIN KELLER等: "Driving simulator study on an emergency steering assist", 《2014 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC)》, 8 October 2014 (2014-10-08) *
张英泽: "城市工况下紧急转向辅助避障系统开发", 《中国硕士学位论文全文数据库 工程科技Ⅱ辑》, 15 November 2019 (2019-11-15) *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114138634A (en) * 2021-11-15 2022-03-04 苏州浪潮智能科技有限公司 Test case selection method and device, computer equipment and storage medium
CN114138634B (en) * 2021-11-15 2024-01-12 苏州浪潮智能科技有限公司 Test case selection method and device, computer equipment and storage medium

Also Published As

Publication number Publication date
CN112580201B (en) 2022-11-08

Similar Documents

Publication Publication Date Title
CN105966396B (en) A kind of vehicle intelligent collision control method based on driver's collision avoidance behavior
Wada et al. Characterization of expert drivers' last-second braking and its application to a collision avoidance system
CN110333730A (en) Verification method, platform and the storage medium of automatic Pilot algorithm expectation function safety
CN111795832B (en) Intelligent driving vehicle testing method, device and equipment
Simon et al. Motion planning for collision mitigation via fem–based crash severity maps
US20230343153A1 (en) Method and system for testing a driver assistance system
CN112580201B (en) Simulation test evaluation method and system for vehicle emergency steering auxiliary system
CN113212429A (en) Automatic driving vehicle safety control method and device
Wang et al. Research on driving behavior decision making system of autonomous driving vehicle based on benefit evaluation model.
Sun et al. An intention-aware and online driving style estimation based personalized autonomous driving strategy
CN114954503A (en) Automatic driving steering fault prediction and redundancy control method and system and electronic equipment
Yu et al. The benefit of simulation test application on the development of autonomous driving system
CN112883500B (en) Intelligent vehicle system early function safety assessment method based on fault injection
Hong et al. Development of a driver's intention determining algorithm for a steering system based collision avoidance system
CN112129543A (en) Method for testing side parking performance of automatic driving vehicle
Liu et al. A human-like shared driving strategy in lane-changing scenario using cooperative LPV/MPC
CN114323698B (en) Real vehicle experiment platform testing method for man-machine co-driving intelligent vehicle
CN114148349A (en) Vehicle personalized following control method based on generation countermeasure simulation learning
CN108839655A (en) A kind of cooperating type self-adaptation control method based on minimum safe spacing
Wang et al. Racing driver modeling based on driving behavior
Zhang et al. Optimization of adaptive cruise control under uncertainty
Atallah et al. Automotive safety verification under temporal failure of adaptive cruise control system using statistical model checking
CN112380724B (en) Simulation test method and system for transverse autonomous lane change auxiliary system of unmanned vehicle
CN113460074B (en) Automatic driving manual takeover request time adjustment method and system
Hatazawa et al. Construction of personalized driver model for car-following behavior on highways using LSTM

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