CN111795832B - Intelligent driving vehicle testing method, device and equipment - Google Patents
Intelligent driving vehicle testing method, device and equipment Download PDFInfo
- Publication number
- CN111795832B CN111795832B CN202010488767.9A CN202010488767A CN111795832B CN 111795832 B CN111795832 B CN 111795832B CN 202010488767 A CN202010488767 A CN 202010488767A CN 111795832 B CN111795832 B CN 111795832B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- target
- virtual target
- test
- parameters
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M17/00—Testing of vehicles
- G01M17/007—Wheeled or endless-tracked vehicles
Abstract
The invention discloses a method, a device and equipment for testing an intelligent driving vehicle, belonging to the technical field of intelligent driving, wherein the method comprises the following steps: responding to a test instruction for testing a vehicle to be tested, wherein the test instruction comprises a test mode; if the test mode is a virtual target mode, acquiring a virtual target parameter from the test instruction; constructing at least one virtual target according to the virtual target parameters; acquiring road environment information of the running road of the vehicle to be detected; and carrying out planning decision based on the road environment information and the at least one virtual target, and controlling the motion of the vehicle to be tested. The invention tests the vehicle by constructing the virtual target, and can reduce the time cost and the resource cost consumed in the preparation process before the test.
Description
Technical Field
The invention relates to the technical field of intelligent driving, in particular to a method, a device and equipment for testing an intelligent driving vehicle.
Background
In the development process of the control system, simulation research is usually performed based on a simulation system, and after the simulation test is completed, a corresponding function test is performed on the real Vehicle, so as to shorten the development cycle of the product and reduce the development cost, and the Hardware-in-the-Loop simulation system (HIL, Hardware in the Loop) and the real Vehicle in-the-Loop simulation system (VIL, Vehicle in the Loop) are commonly used.
In the existing real-vehicle test scheme, test equipment corresponding to functions (such as related tests of automatic emergency automatic functions and the like) needs to be configured, for example, the HIL usually needs to use a HIL cabinet provided by a supplier, and the VIL needs to be provided with a simulation platform provided by the supplier, such as a real-time simulator. In order to construct a test scene, a test target vehicle (such as a related test of an adaptive cruise function) needs to be equipped, or an opportunity (such as a related test of an active lane changing function and an obstacle avoidance function) is created intentionally on a public road. These results in a preparation process before the real vehicle test, which requires a high time cost and resource cost, and may even cause a safety accident.
Disclosure of Invention
The embodiment of the invention provides a method, a device and equipment for testing an intelligent driving vehicle, which aim to solve the technical problem that the prior art needs more time cost and resource cost during actual vehicle test preparation.
In order to achieve the purpose, the invention adopts the technical scheme that:
in one aspect, an embodiment of the present invention provides an intelligent driving vehicle testing method, including:
responding to a test instruction for testing a vehicle to be tested, wherein the test instruction comprises a test mode;
if the test mode is a virtual target mode, acquiring a virtual target parameter from the test instruction;
constructing at least one virtual target according to the virtual target parameters;
acquiring road environment information of the running road of the vehicle to be detected;
and carrying out planning decision based on the road environment information and the at least one virtual target, and controlling the motion of the vehicle to be tested.
On the other hand, the embodiment of the invention provides an intelligent driving vehicle testing device, which comprises:
the system comprises an information receiving module, a test module and a control module, wherein the information receiving module is used for responding to a test instruction for testing a vehicle to be tested, and the test instruction comprises a test mode;
the mode identification module is used for acquiring a virtual target parameter from the test instruction if the test mode is a virtual target mode;
the virtual target construction module is used for constructing at least one virtual target according to the virtual target parameters;
the road environment acquisition module is used for acquiring the road environment information of the running road of the vehicle to be detected;
and the real vehicle control module is used for carrying out planning decision based on the road environment information and the at least one virtual target and controlling the motion of the vehicle to be tested.
In another aspect, an embodiment of the present invention provides a testing device, where the testing device includes a memory and a processor, where the memory stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by the processor to implement the above-mentioned method for testing an intelligent driving vehicle.
The technical scheme of the invention has the following beneficial effects:
the vehicle is tested by constructing the virtual target without preparing test equipment corresponding to a test function and testing the target vehicle, so that the time cost and the resource cost are reduced; meanwhile, a required test scene can be constructed by setting different virtual target parameters, and a corresponding scene test is not required to be carried out by creating opportunities deliberately in public roads, so that the risk of collision with a real target in the test process is avoided, and the safety is improved; by combining the virtual target with the real road environment information, the accuracy of the test can be improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a schematic structural diagram of an intelligent driving vehicle test system according to an embodiment of the present invention.
FIG. 2 is a schematic diagram of a target building system according to an embodiment of the present invention.
Fig. 3 is a schematic flow chart of a test method for an intelligent driving vehicle according to an embodiment of the present invention.
Fig. 4 is a schematic flow chart of controlling the movement of a vehicle to be tested according to an embodiment of the present invention.
Fig. 5 is a schematic flowchart of a process for calculating a position parameter of a vehicle to be measured according to an embodiment of the present invention.
FIG. 6 is a schematic flowchart of a process for calculating a position parameter of a vehicle under test according to an embodiment of the present invention
Fig. 7 is a schematic diagram of an example of a specific test scenario provided in the embodiment of the present invention.
Fig. 8 is a schematic diagram illustrating another specific test scenario provided in the embodiment of the present invention.
Fig. 9 is a schematic structural diagram of an intelligent driving vehicle testing device according to an embodiment of the present invention.
Detailed Description
In order to make those skilled in the art better understand the technical solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
It is noted that the terms "comprises" and "comprising," and any variations thereof, in the description and claims of the present invention, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Referring to fig. 1, a schematic structural diagram of an intelligent driving vehicle testing system according to an embodiment of the present invention is shown, where the system may include a vision camera system 101, a radar system 102, a map positioning system 103, and a rapid control prototype platform 104.
The vision camera system 101 may collect real target information and road environment information within a vehicle view angle range, such as vehicles, pedestrians, lane lines or traffic signs, by using a sensor device such as a camera.
The radar system 102 may collect real target information and road environment information, such as vehicles or pedestrians, within its detection range by using a device such as a radar sensor, which may include but is not limited to millimeter wave radar, laser radar, and the like.
The map positioning system 103 positions the vehicle and outputs information on the vehicle such as the position and road condition.
The rapid control prototype platform 104 is a software platform for rapidly controlling the prototype controller, and after receiving a test instruction of a user to a vehicle, the rapid control prototype platform 104 firstly uses a target construction system to construct/set a test target for testing the vehicle; and then, fusing the test target with the real target information, the road environment information and the related position information by using a functional algorithm system, determining a control strategy for controlling the vehicle, and then controlling the motion of the vehicle according to the control strategy.
The functions related to the functional algorithm system can be but are not limited to a lane keeping function, a forward collision early warning function, an automatic emergency braking function, an adaptive cruise function, a deflector rod lane changing function, an active lane changing function, an automatic on-off ramp function, an active obstacle avoidance function and the like.
The target construction system can comprise a virtual target construction module, a real target setting module and a target selection module, the target construction system can output a virtual target and/or a real target as a test target, and the target construction system can determine according to a test mode selected by a user when outputting the test target. In specific implementation, the virtual target construction module constructs a virtual target through virtual target parameters, the real target determination module obtains a real target and corresponding real target parameters through fusing data of the visual camera system and the radar system, and the target selection module finally outputs a test target.
Referring specifically to fig. 2, a schematic structural diagram of a target building system according to an embodiment of the present invention is shown. When the vehicle needs to be tested, different test targets are selected according to the test mode. If the test mode is a virtual target mode, the virtual target construction module constructs a virtual target according to virtual target parameters, the moment of selecting the test mode is taken as an initial moment, the absolute parameters of the virtual target are calculated in real time in the vehicle test process, target relative parameters relative to the vehicle to be tested are obtained based on the parameters of the vehicle to be tested, and the virtual target construction and the virtual target parameter acquisition are realized by increasing noise processing and other modes; if the test mode is a real target mode, the real target setting module fuses the relevant information output by each sensor to obtain a real target and corresponding parameters thereof; the target construction system can select and output the virtual target and/or the real target as a test target according to the target selection module so as to test the vehicle.
Referring to fig. 3, a flow chart of a testing method for an intelligent driving vehicle according to an embodiment of the present invention is shown. As shown in fig. 3, the method may include:
s301, responding to a test instruction for testing the vehicle to be tested, wherein the test instruction comprises a test mode.
In the embodiment of the invention, the vehicle to be tested is equipped with a related automatic driving function or an auxiliary driving function, and the equipped functions can comprise a lane keeping function, a forward collision early warning function, an automatic emergency braking function, a self-adaptive cruise function, a deflector rod lane changing function, an active lane changing function, an automatic on-off ramp function, an active obstacle avoidance function and the like. When the functions equipped on the vehicle to be tested need to be tested, a test mode for testing can be set, and then different test parameters are customized for different test modes, wherein the test modes can comprise a virtual target mode and a real target mode.
S302, if the test mode is the virtual target mode, obtaining the virtual target parameters from the test instruction.
In the embodiment of the invention, if the test mode is the virtual mode, the corresponding function of the vehicle to be tested is tested by establishing the virtual target. The virtual target parameters can comprise virtual target types, virtual target number, target attributes and the like, the virtual target types represent the types of virtual targets to be constructed, and the virtual target types can comprise pedestrians, vehicles and traffic signs; the number of the virtual targets represents the number of the virtual targets to be constructed; the target attribute represents an attribute specific to the virtual target, for example, the target attribute of which the virtual target type is a vehicle may include a longitudinal and transverse position, a longitudinal and transverse acceleration, a heading angle, a target width, a target quality, a reliability and the like, and the target attribute of which the virtual target is a traffic sign may include a speed limit rate and the like.
The position of the corresponding virtual target on the running road of the vehicle to be detected can be set through the target attribute, if the pedestrian or the vehicle is static or moving, the movement of the virtual target can be controlled by setting the speed, the acceleration, the course angle and the like of the pedestrian or the vehicle. When the target type is a vehicle, the type or model of the vehicle may also be set to test the response of the function in the face of vehicles of different models.
In practical applications, the configuration of the virtual target parameters may be provided by an interface or a configuration file, the virtual target parameters may include a plurality of parameter sets, each parameter set corresponds to a parameter of a virtual target, and the parameters of each virtual target may be the same or different, for example, a virtual target of a type of traffic sign may be set, a virtual target of a type of vehicle may be set, and the configuration of different test scenarios may be implemented by adjusting the parameters of each virtual target. For example, a moving vehicle may be arranged right in front of the vehicle to be tested, a speed limit sign may be arranged beside the driving road of the vehicle to be tested, and the types of the virtual targets may be combined arbitrarily.
S303, constructing at least one virtual target according to the virtual target parameters.
In the development process of the intelligent driving function algorithm, the development efficiency can be improved to a great extent and the development cost can be reduced by using a Rapid Control model (RCP). After the simulation test is completed, the functional algorithm can be verified on a real vehicle by using the RCP platform. Therefore, in the embodiment of the invention, the target for testing the vehicle to be tested can be constructed or set based on the rapid prototyping control platform, and the verification of the corresponding function can be carried out.
When the virtual target is constructed, the virtual target is constructed by reading the parameter information in the virtual target parameters, and one or more virtual targets can be constructed as required. Since there are a limited number of targets on the road ahead of the vehicle when the vehicle is traveling on the actual road and there are a limited number of targets detected by the sensors mounted on the vehicle, the number of virtual targets can be limited when constructing the virtual targets to better suit the actual traffic scene.
In view of this, in one possible embodiment, constructing at least one virtual target according to the virtual target parameters may include: and constructing at least one virtual target according to the virtual target parameters based on the rapid prototyping control platform, wherein the types of the virtual targets comprise pedestrians, vehicles and traffic signs, and the number of the virtual targets does not exceed a preset target threshold value.
It should be noted that the preset target threshold may be set as needed, or may be obtained by fusing data of each sensor on the current vehicle, which is not limited herein.
And S304, acquiring the road environment information of the running road of the vehicle to be detected.
In the embodiment of the invention, the road environment information can be obtained through the camera, the millimeter wave radar or the laser radar and other sensors which are arranged on the vehicle, and the road environment information can comprise all road condition information which can be identified by the vehicle, such as obstacle information, lane line information, lane number information, lane guide line information, traffic marks and the like. By adopting a real road scene and real visual input, the test result under the virtual target mode can be ensured to be more accurate.
S305, planning decision is made based on the road environment information and at least one virtual target, and the motion of the vehicle to be tested is controlled.
The control of the movement of the vehicle to be tested mainly comprises the control of the speed, the position, the driving direction and the like of the vehicle to be tested. Referring to fig. 4, a schematic flow chart of controlling the motion of a vehicle under test according to an embodiment of the present invention is shown. As shown in fig. 4, step S305 may include:
s3051, calculating position parameters of the vehicle to be measured, wherein the position parameters comprise a transverse position, a longitudinal position and a course angle.
In the embodiment of the invention, the transverse position, the longitudinal position and the course angle of the vehicle to be driven can be obtained by calculation according to the transverse position variation, the longitudinal position variation and the course angle variation in a sampling period.
Referring to fig. 5 in particular, a schematic flowchart of calculating a position parameter of a vehicle to be tested according to an embodiment of the present invention is shown. As shown in fig. 5, performing step S3051, calculating the position parameter of the vehicle to be measured may include:
s30511, collecting the longitudinal speed and the yaw rate of the vehicle to be measured.
Generally, parameters such as longitudinal speed, longitudinal acceleration, yaw rate, steering wheel angle and the like of the vehicle can be calculated or directly obtained from data collected by relevant sensors mounted on the vehicle, and more schemes are available and are not described in detail herein.
S30512, calculating the position variation of the vehicle to be measured according to the longitudinal speed.
At the current sampling moment, the position variation of the vehicle to be detected can be calculated according to the speed and the sampling period of the vehicle to be detected, and if the position variation of the vehicle to be detected is represented by the Detad, the Detad can be represented as:
Detad＝V·T
where V represents the longitudinal speed of the vehicle under test and T represents the sampling period.
S30513, judging whether the longitudinal speed is less than or equal to a preset speed threshold value.
In the embodiment of the invention, the calculation mode of the curvature can be determined according to the longitudinal speed of the vehicle to be measured, and when the longitudinal speed is less than or equal to the preset speed threshold, the step S30514 is executed, and the curvature is calculated through the two-degree-of-freedom vehicle model; when the longitudinal velocity is greater than the preset velocity threshold, step S30515 is performed to calculate the curvature directly from the yaw rate.
And S30514, calculating the curvature of the vehicle to be measured according to the two-degree-of-freedom vehicle model.
Specifically, if Curvature is used to represent the Curvature of the vehicle to be measured, when the vehicle speed of the vehicle to be measured is small, that is, the longitudinal speed is less than or equal to the preset speed threshold, the Curvature may be represented as:
wherein R represents the turning radius, WheelAngle represents the wheel turning angle, B represents the wheel track, m represents the mass of the vehicle to be measured, and l r Representing the distance of the rear axle to the center of mass, C f Represents a front wheel yaw coefficient l f Representing the distance of the front axle to the centre of mass, C r The rear wheel slip coefficient is indicated.
The wheel angle WheelAngle can be calculated by multiplying the steering wheel angle by the steering wheel angle transmission ratio, i.e.:
WheelAngle＝PinionSteerAg·SteerWhlAgRat
wherein PinionSteerAg represents the steering wheel angle of the vehicle to be tested, and SteerWhlAgRat represents the steering wheel angle transmission ratio.
And S30515, calculating the curvature of the vehicle to be measured according to the yaw velocity.
When the speed of the vehicle to be measured is large, namely the longitudinal speed is greater than a preset speed threshold, the curvature is the ratio of the yaw velocity to the longitudinal speed, namely:
wherein YawRate represents the yaw rate of the vehicle under test.
And S30516, calculating to obtain the position parameter of the vehicle to be measured according to the curvature and the position variation.
In the embodiment of the invention, the prediction mode of the position of the vehicle to be detected is determined according to the curvature, and the transverse position variation and the longitudinal position variation are obtained. Specifically, as shown in fig. 6, step S30516 may include:
and S305161, calculating the course angle variation of the vehicle to be measured according to the curvature and the position variation.
Specifically, the course angle variation may be calculated by multiplying the curvature by the position variation, and if the course angle variation is represented by Detah, the following expression is provided:
Detah＝Curvature·Detad
s305162, judging whether the curvature is less than or equal to a preset curvature threshold value.
In the embodiment of the invention, a preset curvature threshold value is set according to the size of the curvature, when the curvature is smaller than or equal to the preset curvature threshold value, the position of the vehicle to be detected is predicted according to a straight line method, and step S305163 is executed; and when the curvature is larger than the preset curvature threshold, predicting the position of the vehicle to be detected according to a curve method, and executing the step S305164.
S305163, calculating to obtain the transverse position variation and the longitudinal position variation of the vehicle to be measured according to the position variation and the course angle variation.
Specifically, the lateral position variation Detax and the longitudinal position variation Detay of the vehicle to be measured may be respectively expressed as:
Detax＝Detad·cos(Detah)
Detay＝Detad·sin(Detah)
s305164, calculating to obtain the transverse position variation and the longitudinal position variation of the vehicle to be measured according to the curvature and the course angle variation.
Specifically, the lateral position variation Detax and the longitudinal position variation Detay of the vehicle to be measured may be respectively expressed as:
Detax＝sin(Detah)/Curvature
Detay＝(1-cos(Detah))/Curvature
s305165, calculating to obtain the position parameter of the vehicle to be measured according to the transverse position variation, the longitudinal position variation and the course angle variation.
In specific implementation, the transverse position in the previous sampling period and the transverse position variation in the current sampling period can be superposed to obtain the transverse position in the current sampling period, and the longitudinal position and the course angle can be calculated in the same way. For convenience of description, the transverse position of the vehicle to be measured is represented by the larterposition, the longitudinal position of the vehicle to be measured is represented by the LongtudinalPosition, and the heading angle of the vehicle to be measured is represented by the hosthheadingangle.
It should be noted that the preset speed threshold and the preset curvature threshold may be set according to a specific test scenario or a function to be tested, and the curvature is related to a corresponding curvature change rate, so that the preset curvature threshold may also be set according to the curvature change rate, which is not limited herein.
S3052, calculating relative target parameters of the at least one virtual target relative to the vehicle to be measured according to the transverse position, the longitudinal position and the course angle.
In the embodiment of the invention, the relative target parameters can be obtained by calculating the speed, the curvature, the longitudinal position and the transverse position of each virtual target and then according to the transverse position, the longitudinal position and the course angle of the vehicle to be detected.
Specifically, at the initial time of the test, each parameter value of the virtual target is assigned according to the virtual target parameter of the set value, and at the time k, each parameter value can be calculated based on the sampling period and the parameter value at the previous time. When the virtual target mode is started, the central position of the rear axle of the vehicle to be detected is taken as the origin of coordinates, and if SP is used k Representing the velocity of the virtual target at time k, targetA k Represents the acceleration, Cur, of the virtual target at time k k Representing the curvature of the virtual object at time k, using CurRate k Representing the rate of change of curvature of a virtual target at time k, DeltaDis k Indicating the amount of change in the distance of the virtual target at time k, targgg k Indicating the course angle of the virtual target at time k, TarLgtPos k Indicating the vertical position of the virtual target at time k, TarLatPos k The horizontal position of the virtual target at the time k is shown, the speed, the curvature, the distance variation, the vertical position and the horizontal position of the virtual target can be respectively shown as follows:
SP k ＝SP k-1 +TargetA k ·T,
Cur k ＝Cur k-1 +CurRate k-1 ·T,
DeltaDis k ＝f(SP k ，TargetA k ),
TarLgtPos k ＝cos(TargHG k )·DeltaDis k +TarLgtPos k-1 ,
TarLatPos k ＝sin(TargHG k )·DeltaDis k +TarLatPos k-1 .
where T denotes the sampling period, f (SP) k ，TargetA k ) Indicating about SP k And TargetA k The function of (d), i.e. the distance change, can be calculated from the velocity and acceleration.
Then, the absolute lateral position difference between the virtual target and the vehicle under test can be expressed as:
PosnLatG＝TarLatPos-LaterPosition
the absolute longitudinal position difference between the virtual target and the vehicle under test can be expressed as:
PosnLgtG＝TarLgtPos-LongtudinalPosition
the absolute distance between the virtual target and the vehicle under test can be expressed as:
the relative target parameters of each virtual target relative to the vehicle to be tested at least comprise a relative course angle, a relative transverse position, a relative longitudinal position, a relative transverse speed, a relative longitudinal speed, a relative transverse acceleration and a relative longitudinal acceleration, wherein the calculation of the relative transverse position and the relative longitudinal position is related to the virtual target in front of or behind the vehicle to be tested. Specifically, the parameter values of the respective relative target parameters can be calculated as shown in the following table:
and S3053, combining the relative target parameters with the road environment information, and controlling the motion of the vehicle to be detected.
In the embodiment of the invention, the vehicle to be tested is subjected to transverse or longitudinal coupling control based on the relative target parameters in combination with road environment information, such as real road scenes including lane lines or lane numbers.
In one possible embodiment, before performing step S3053, the method for testing a smart-driving vehicle may further include: and carrying out noise adding processing on the relative target parameters. By performing the noise-adding processing on the relative target parameter, for example, performing the noise-adding processing on the relative lateral-longitudinal speed, the relative lateral-longitudinal acceleration, and the like, the output relative target parameter can be made closer to the output characteristic of the real sensor.
In the embodiment of the invention, in the process of controlling the movement of the vehicle to be tested, more scenes can be constructed by adjusting the corresponding parameters of the virtual target, so as to meet the requirement of the function test of the vehicle to be tested.
In view of this, in one possible embodiment, the intelligent driving vehicle testing method may further include: and responding to the modification instruction aiming at the virtual target parameter, and adjusting the running state of at least one virtual target according to the modification instruction.
In addition, the test mode can also be switched, for example, if the vehicle to be tested runs on a public road, the traffic scene on the public road is detected to be suitable for the current test scene, and the real target test can be carried out by switching the virtual target mode into the real target mode; and if no corresponding test scene exists on the public road, the test mode can be switched to the virtual target mode to carry out virtual target test.
In one possible embodiment, the intelligent driving vehicle test method may further include: responding to a switching instruction aiming at the test mode, and switching the test mode into a real target mode or a virtual target mode according to the switching instruction, wherein the real target mode adopts at least one real target to test the vehicle to be tested, and the real target is a target detected by each real sensor arranged on the vehicle to be tested. In specific implementation, the real target may be a target result obtained by fusing data acquired by each or various sensors.
The intelligent driving vehicle testing method provided by the embodiment of the invention is more fully explained in combination with a specific function testing scene.
Referring to fig. 7, a schematic diagram of a test scenario for Adaptive Cruise Control (ACC) functionality is shown. Fig. 7 is a Stop & Go scene in the ACC function, in which a vehicle to be tested normally runs on a public road, the ACC function is turned on, the test mode is switched to a virtual target mode, and a virtual target type is set right in front of the vehicle to be tested as a virtual target of the vehicle. And when the test is started, the virtual target runs at a certain speed, the virtual target slowly decelerates until the vehicle stops by adjusting the parameters of the virtual target after a certain time, and then the virtual target accelerates to move ahead. The vehicle to be tested keeps a certain safe distance with the virtual target at the beginning according to the time distance set by the ACC, then the vehicle to be tested slowly reduces the speed and accurately stops following the deceleration and parking process of the corresponding virtual target, and the vehicle to be tested immediately starts and accelerates after the virtual target starts and accelerates. The stability of the ACC following, the following Stop and re-start performance of the ACC-Stop & Go can be detected through the test.
Please refer to fig. 8, which shows a schematic diagram of a test scenario for the active lane change function. In fig. 8, the vehicle to be tested normally runs on a public road, and starts ACC, intelligent navigation (power Assist, PA), lever pulling lane changing function, and active lane changing function, and switches the test mode to the virtual target mode. The virtual target is arranged in front of the vehicle to be tested and runs at a certain speed, the running speed of the virtual target is less than the speed set by the ACC, the vehicle to be tested slowly starts to decelerate after detecting the virtual target, and the driver starts to actively change lanes after turning on a turn light.
Of course, the virtual target mode is not limited to be applied to the test scenario shown above, and can also be applied to various aspects of real vehicle testing. For example, a balloon car, a dummy, etc. in an AEB (automated Emergency Brake) test may be replaced with a virtual target; in the active lane change test process, various target vehicles with risks around the vehicle to be tested can be replaced by virtual targets; and replacing the front vehicle which is to be overtaken by the virtual target in the micro obstacle avoidance test, and the like.
In the existing real-vehicle test, test equipment corresponding to functions needs to be configured, for example, the HIL usually needs to use a HIL cabinet provided by a supplier, and the VIL needs to be provided with a simulation platform such as a real-time simulator and the like provided by the supplier. In addition, a large amount of time is needed to construct a corresponding scene in the early stage, for example, a target vehicle is equipped in front of a vehicle to be tested, the target vehicle needs to be configured with corresponding personnel to adjust the speed, the position and the like according to different functions so as to be dynamically matched with the vehicle to be tested, the scene construction is not reusable, and when the functions need to be retested, the same scene needs to be reconstructed. In practical applications, severe asymmetries typically occur where the device is prepared for several hours, and actually tested for several minutes.
In the intelligent driving test method provided by the embodiment of the invention, the virtual target is used for replacing various test devices and target vehicles, and the virtual target parameters can be customized according to the scene requirements, so that a specific scene is directly and quickly constructed, and corresponding functions can be controlled according to the characteristics of the virtual target, thereby improving the test efficiency to a great extent and reducing the resources and time required by the test.
According to the technical scheme provided by the embodiment, the intelligent driving vehicle testing method provided by the embodiment of the invention tests the vehicle by constructing the virtual target without preparing the testing equipment and the testing target vehicle corresponding to the testing function, so that the time cost and the resource cost are reduced; meanwhile, a required test scene can be constructed by setting different virtual target parameters, and a corresponding scene test is not required to be carried out by creating opportunities deliberately in public roads, so that the risk of collision with a real target in the test process is avoided, and the safety is improved; by combining the virtual target with the real road environment information, the accuracy of the test can be improved.
Referring to fig. 9, a schematic structural diagram of an intelligent driving vehicle testing apparatus according to an embodiment of the present invention is shown. As shown in fig. 9, the apparatus 900 may include:
the information receiving module 901 is used for responding to a test instruction for testing a vehicle to be tested, wherein the test instruction comprises a test mode;
a mode identification module 902, configured to obtain a virtual target parameter from the test instruction if the test mode is a virtual target mode;
a virtual target construction module 903, configured to construct at least one virtual target according to the virtual target parameters;
a road environment obtaining module 904, configured to obtain road environment information of a road on which the vehicle to be detected travels;
and the real vehicle control module 905 is configured to perform a planning decision based on the road environment information and the at least one virtual target, and control the motion of the vehicle to be detected.
In one possible embodiment, the virtual object constructing module 903 is specifically configured to construct at least one virtual object according to the virtual object parameters based on a rapid prototyping control platform, where the types of the virtual objects include pedestrians, vehicles, and traffic signs, and the number of the virtual objects does not exceed a preset object threshold.
In one possible embodiment, the real vehicle control module 905 includes a vehicle position acquisition unit, a relative position acquisition unit, and a control unit:
the vehicle position acquisition unit is used for calculating position parameters of the vehicle to be detected, wherein the position parameters comprise a transverse position, a longitudinal position and a course angle;
the relative position acquisition unit is used for calculating relative target parameters of the at least one virtual target relative to the vehicle to be detected according to the transverse position, the longitudinal position and the course angle;
and the control unit is used for combining the relative target parameters with the road environment information and controlling the motion of the vehicle to be tested.
In one possible embodiment, the vehicle position acquisition unit is further configured to:
collecting the longitudinal speed and the yaw angular speed of the vehicle to be detected;
calculating the position variation of the vehicle to be detected according to the longitudinal speed;
when the longitudinal speed is smaller than or equal to a preset speed threshold value, calculating according to a two-degree-of-freedom vehicle model to obtain the curvature of the vehicle to be measured;
when the longitudinal speed is greater than the preset speed threshold, calculating to obtain the curvature of the vehicle to be measured according to the yaw velocity;
and calculating to obtain the position parameters of the vehicle to be measured according to the curvature and the position variation.
In one possible embodiment, the vehicle position acquisition unit is further configured to:
calculating the course angle variation of the vehicle to be detected according to the curvature and the position variation;
when the curvature is smaller than or equal to a preset curvature threshold, calculating to obtain the transverse position variation and the longitudinal position variation of the vehicle to be detected according to the position variation and the course angle variation;
when the curvature is larger than the preset curvature threshold, calculating to obtain the transverse position variation and the longitudinal position variation of the vehicle to be detected according to the curvature and the course angle variation;
and calculating to obtain the position parameters of the vehicle to be measured according to the transverse position variation, the longitudinal position variation and the course angle variation.
In one possible embodiment, the real vehicle control module 905 further includes a preprocessing unit, and the preprocessing unit is configured to perform denoising processing on the relative target parameter.
In one possible embodiment, the apparatus 900 may further include a scene change module, configured to, in response to a modification instruction for the virtual target parameter, adjust the driving state of the at least one virtual target according to the modification instruction.
In one possible embodiment, the apparatus 900 may further include a mode switching module, configured to, in response to a switching instruction for the test mode, switch the test mode to a real target mode or a virtual target mode according to the switching instruction, where the real target mode tests the vehicle to be tested using at least one real target, and the real target is a target detected by each real sensor installed on the vehicle to be tested.
It should be noted that, when the apparatus/system provided in the foregoing embodiment implements the functions thereof, only the division of the functional modules is illustrated, and in practical applications, the functions may be distributed and completed by different functional modules according to needs, that is, the internal structure of the apparatus may be divided into different functional modules to complete all or part of the functions described above. In addition, the device/system and the method embodiments provided by the above embodiments belong to the same concept, and the specific implementation process thereof is described in the method embodiments, which is not described herein again.
The embodiment of the invention also provides a test device, which comprises a memory and a processor, wherein at least one instruction or at least one program is stored in the memory, and the at least one instruction or the at least one program is loaded and executed by the processor to realize the intelligent driving vehicle test method provided by the above method embodiment.
It should be noted that: the sequence of the above embodiments of the present invention is only for description, and does not represent the advantages or disadvantages of the embodiments. And that specific embodiments have been described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the device and electronic apparatus embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference may be made to some descriptions of the method embodiments for relevant points.
The foregoing description has disclosed fully preferred embodiments of the present invention. It should be noted that those skilled in the art can make modifications to the embodiments of the present invention without departing from the scope of the appended claims. Accordingly, the scope of the appended claims is not to be limited to the specific embodiments described above.
Claims (9)
1. An intelligent driving vehicle testing method, comprising:
responding to a test instruction for testing a vehicle to be tested, wherein the test instruction comprises a test mode;
if the test mode is a virtual target mode, acquiring virtual target parameters from the test instruction;
constructing at least one virtual target according to the virtual target parameters;
acquiring road environment information of the running road of the vehicle to be detected;
calculating the position parameters of the vehicle to be detected, wherein the position parameters comprise a transverse position, a longitudinal position and a course angle;
calculating a relative target parameter of the at least one virtual target relative to the vehicle to be detected according to the transverse position, the longitudinal position and the course angle;
and combining the relative target parameters with the road environment information to control the motion of the vehicle to be detected.
2. The method of claim 1, wherein the constructing at least one virtual target according to the virtual target parameters comprises:
and constructing at least one virtual target according to the virtual target parameters based on a rapid prototyping control platform, wherein the types of the virtual targets comprise pedestrians, vehicles and traffic signs, and the number of the virtual targets does not exceed a preset target threshold value.
3. The method of claim 1, wherein the calculating the position parameters of the vehicle under test comprises:
acquiring the longitudinal speed and the yaw angular speed of the vehicle to be detected;
calculating the position variation of the vehicle to be detected according to the longitudinal speed;
when the longitudinal speed is smaller than or equal to a preset speed threshold value, calculating according to a two-degree-of-freedom vehicle model to obtain the curvature of the vehicle to be measured;
when the longitudinal speed is greater than the preset speed threshold, calculating to obtain the curvature of the vehicle to be measured according to the yaw velocity;
and calculating to obtain the position parameters of the vehicle to be detected according to the curvature and the position variable quantity.
4. The method according to claim 3, wherein the calculating the position parameter of the vehicle under test according to the curvature and the position variation comprises:
calculating the course angle variable quantity of the vehicle to be measured according to the curvature and the position variable quantity;
when the curvature is smaller than or equal to a preset curvature threshold, calculating to obtain the transverse position variation and the longitudinal position variation of the vehicle to be detected according to the position variation and the course angle variation;
when the curvature is larger than the preset curvature threshold, calculating to obtain the transverse position variation and the longitudinal position variation of the vehicle to be detected according to the curvature and the course angle variation;
and calculating to obtain the position parameters of the vehicle to be measured according to the transverse position variation, the longitudinal position variation and the course angle variation.
5. The method of claim 1, wherein prior to said combining said relative target parameter with said road environment information to control the movement of said vehicle under test, said method further comprises:
and carrying out noise adding processing on the relative target parameters.
6. The method of claim 1, further comprising:
in response to a modification instruction for the virtual target parameter, adjusting the driving state of the at least one virtual target according to the modification instruction.
7. The method of claim 1, further comprising:
responding to a switching instruction aiming at the test mode, and switching the test mode into a real target mode or a virtual target mode according to the switching instruction, wherein the real target mode adopts at least one real target to test the vehicle to be tested, and the real target is a target detected by each real sensor arranged on the vehicle to be tested.
8. An intelligent driving vehicle testing device, comprising:
the system comprises an information receiving module, a test module and a control module, wherein the information receiving module is used for responding to a test instruction for testing a vehicle to be tested, and the test instruction comprises a test mode;
the mode identification module is used for acquiring a virtual target parameter from the test instruction if the test mode is a virtual target mode;
the virtual target construction module is used for constructing at least one virtual target according to the virtual target parameters;
the road environment acquisition module is used for acquiring road environment information of a running road of the vehicle to be detected;
the real vehicle control module is used for making planning decisions based on the road environment information and the at least one virtual target and controlling the motion of the vehicle to be tested, and comprises:
calculating the position parameters of the vehicle to be detected, wherein the position parameters comprise a transverse position, a longitudinal position and a course angle;
calculating a relative target parameter of the at least one virtual target relative to the vehicle to be detected according to the transverse position, the longitudinal position and the course angle;
and combining the relative target parameters with the road environment information to control the motion of the vehicle to be detected.
9. A test device comprising a memory and a processor, the memory having stored therein at least one instruction or at least one program, the at least one instruction or at least one program being loaded and executed by the processor to implement the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010488767.9A CN111795832B (en) | 2020-06-02 | 2020-06-02 | Intelligent driving vehicle testing method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010488767.9A CN111795832B (en) | 2020-06-02 | 2020-06-02 | Intelligent driving vehicle testing method, device and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111795832A CN111795832A (en) | 2020-10-20 |
| CN111795832B true CN111795832B (en) | 2022-09-02 |
Family
ID=72806248
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010488767.9A Active CN111795832B (en) | 2020-06-02 | 2020-06-02 | Intelligent driving vehicle testing method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111795832B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112649208A (en) * | 2020-11-30 | 2021-04-13 | 北京智能车联产业创新中心有限公司 | Device and method for testing emergency braking function of automatic driving vehicle |
| CN113447276A (en) * | 2021-05-26 | 2021-09-28 | 中国电子产品可靠性与环境试验研究所（（工业和信息化部电子第五研究所）（中国赛宝实验室）） | Vehicle testing system and vehicle testing method |
| CN113460050B (en) * | 2021-07-22 | 2022-11-15 | 上汽通用五菱汽车股份有限公司 | Vehicle follow-up stop control method and device and computer readable storage medium |
| CN113342704B (en) * | 2021-08-06 | 2021-11-12 | 腾讯科技（深圳）有限公司 | Data processing method, data processing equipment and computer readable storage medium |
| CN113484851B (en) * | 2021-09-08 | 2021-11-16 | 北京理工大学深圳汽车研究院(电动车辆国家工程实验室深圳研究院) | Simulation test system and method for vehicle-mounted laser radar and complete vehicle in-loop test system |
| CN114067459B (en) * | 2021-09-10 | 2023-08-01 | 中国人民解放军63966部队 | Motor vehicle safety performance test system |
| CN114089773B (en) * | 2022-01-11 | 2022-05-27 | 深圳佑驾创新科技有限公司 | Test method, device, equipment and storage medium for automatic driving vehicle |
| CN115493857B (en) * | 2022-11-16 | 2023-03-21 | 苏州挚途科技有限公司 | Method and device for determining automatic emergency braking parameters and processor |
| CN116734892B (en) * | 2023-08-15 | 2023-11-03 | 腾讯科技（深圳）有限公司 | Method, device, equipment and medium for processing driving data |
| CN117074049B (en) * | 2023-10-19 | 2024-01-02 | 中汽传媒(天津)有限公司 | Intelligent driving vehicle road cloud testing system based on virtual-real combination |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9836895B1 (en) * | 2015-06-19 | 2017-12-05 | Waymo Llc | Simulating virtual objects |
| CN108897216A (en) * | 2018-07-03 | 2018-11-27 | 吉林大学 | A kind of intelligent automobile model prediction decision-making technique based on the virtual field of force in region |
| CN109580252A (en) * | 2018-12-29 | 2019-04-05 | 驭势科技（北京）有限公司 | Intelligent driving vehicle testing method, on-vehicle control apparatus and the test macro of a kind of vehicle in ring |
| CN109808687B (en) * | 2019-01-17 | 2021-09-21 | 福瑞泰克智能系统有限公司 | Driving assistance method, device and equipment |
-
2020
- 2020-06-02 CN CN202010488767.9A patent/CN111795832B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111795832A (en) | 2020-10-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111795832B (en) | Intelligent driving vehicle testing method, device and equipment | |
| CN109421742B (en) | Method and apparatus for monitoring autonomous vehicles | |
| CN109421738B (en) | Method and apparatus for monitoring autonomous vehicles | |
| US10943414B1 (en) | Simulating virtual objects | |
| CN112703459B (en) | Iterative generation of confrontational scenarios | |
| CN110562258B (en) | Method for vehicle automatic lane change decision, vehicle-mounted equipment and storage medium | |
| Naranjo et al. | Using fuzzy logic in automated vehicle control | |
| US20190235521A1 (en) | System and method for end-to-end autonomous vehicle validation | |
| Belbachir et al. | Simulation-driven validation of advanced driving-assistance systems | |
| CN112819968B (en) | Test method and device for automatic driving vehicle based on mixed reality | |
| WO2020079698A1 (en) | Adas systems functionality testing | |
| CN114077541A (en) | Method and system for validating automatic control software for an autonomous vehicle | |
| CN110174274A (en) | A kind of modification method and device of intelligent driving algorithm | |
| Gietelink et al. | Development of a driver information and warning system with vehicle hardware-in-the-loop simulations | |
| EP4020113A1 (en) | Dynamic model evaluation package for autonomous driving vehicles | |
| EP3869341A1 (en) | Play-forward planning and control system for an autonomous vehicle | |
| CN111240224A (en) | Multifunctional simulation system for vehicle automatic driving technology | |
| CN117130298A (en) | Method, device and storage medium for evaluating an autopilot system | |
| CN115907250A (en) | Learning-based commenter for adjusting a motion planner of an autonomously driven vehicle | |
| CN112985825B (en) | Method for determining the ride stability of an autopilot system | |
| CN112446466A (en) | Measuring confidence in deep neural networks | |
| CN112415910A (en) | Method for evaluating software components of a Sil environment | |
| EP4082856A2 (en) | E2e learning-based evaluator for an autonomous driving vehicle | |
| CN115755865A (en) | Commercial vehicle driving assistance hardware in-loop test system and method | |
| CN115859821A (en) | Method and system for creating a simulated environment for simulating an autonomously driven vehicle |
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 |