CN115616937A - Automatic driving simulation test method, device, equipment and computer readable medium - Google Patents

Automatic driving simulation test method, device, equipment and computer readable medium Download PDF

Info

Publication number
CN115616937A
CN115616937A CN202211533256.XA CN202211533256A CN115616937A CN 115616937 A CN115616937 A CN 115616937A CN 202211533256 A CN202211533256 A CN 202211533256A CN 115616937 A CN115616937 A CN 115616937A
Authority
CN
China
Prior art keywords
simulation test
test
scene data
simulation
static
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
CN202211533256.XA
Other languages
Chinese (zh)
Other versions
CN115616937B (en
Inventor
张�雄
李敏
蒋建辉
胡禹超
蔡仲辉
申苗
刘智睿
艾永军
黄家琪
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.)
GAC Aion New Energy Automobile Co Ltd
Original Assignee
GAC Aion New Energy Automobile Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by GAC Aion New Energy Automobile Co Ltd filed Critical GAC Aion New Energy Automobile Co Ltd
Priority to CN202211533256.XA priority Critical patent/CN115616937B/en
Publication of CN115616937A publication Critical patent/CN115616937A/en
Application granted granted Critical
Publication of CN115616937B publication Critical patent/CN115616937B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B17/00Systems involving the use of models or simulators of said systems
    • G05B17/02Systems involving the use of models or simulators of said systems electric
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00Computer-aided design [CAD]
    • G06F30/20Design optimisation, verification or simulation

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Computer Hardware Design (AREA)
  • Evolutionary Computation (AREA)
  • Geometry (AREA)
  • General Engineering & Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

Embodiments of the present disclosure disclose automated driving simulation testing methods, apparatus, devices, and computer readable media. One embodiment of the method comprises: acquiring simulation test scene data corresponding to the functional test instruction; off-line correction processing is carried out on dynamic scene data included in the simulation test scene data to obtain corrected dynamic scene data; establishing an initialization simulation test environment based on the corrected dynamic scene data and the corrected static scene data; executing automatic driving simulation test operation in an initialization simulation test environment to generate a simulation test planning path set; and generating a first automatic driving simulation test result in response to the fact that all the simulation test planning paths in the simulation test planning path set meet the preset path conditions. This embodiment may improve the accuracy of the test results.

Description

Automatic driving simulation test method, device, equipment and computer readable medium
Technical Field
The embodiment of the disclosure relates to the technical field of computers, in particular to an automatic driving simulation test method, device, equipment and a computer readable medium.
Background
Automated driving simulation testing is a technique for testing automated driving functions. At present, when an automatic driving simulation test is carried out, the method generally adopted is as follows: and playing back real vehicle data for analysis to determine the problems of the automatic driving function in an off-line test mode, or simulating the automatic driving function for testing by a common simulation test method to determine the problems of the automatic driving function.
However, the inventors have found that when automated driving simulation tests are performed in the above manner, the following technical problems often occur:
the off-line test mode is difficult to analyze aiming at the current vehicle and dynamic obstacle vehicle interaction scene, so that the test is difficult to be carried out comprehensively, and the accuracy of the test result in the interaction aspect is low.
The above information disclosed in this background section is only for enhancement of understanding of the background of the inventive concept and, therefore, it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art.
Disclosure of Invention
This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.
Some embodiments of the present disclosure propose automated driving simulation test methods, apparatuses, devices and computer readable media to address one or more of the technical problems mentioned in the background section above.
In a first aspect, some embodiments of the present disclosure provide an automated driving simulation test method, the method comprising: responding to a received functional test instruction for an automatic driving path planning module, and acquiring simulation test scene data corresponding to the functional test instruction, wherein the simulation test scene data comprises static scene data and dynamic scene data; off-line correction processing is carried out on dynamic scene data included in the simulation test scene data to obtain corrected dynamic scene data; establishing an initialization simulation test environment based on the corrected dynamic scene data and the static scene data; executing automatic driving simulation test operation in the initialization simulation test environment to generate a simulation test planning path set; and generating a first automatic driving simulation test result in response to the fact that all the simulation test planning paths in the simulation test planning path set meet the preset path conditions.
In a second aspect, some embodiments of the present disclosure provide an automated driving simulation test apparatus, the apparatus comprising: the system comprises an acquisition unit, a processing unit and a control unit, wherein the acquisition unit is configured to respond to a received functional test instruction aiming at an automatic driving path planning module and acquire simulation test scene data corresponding to the functional test instruction, and the simulation test scene data comprises static scene data and dynamic scene data; the correction processing unit is configured to perform offline correction processing on dynamic scene data included in the simulation test scene data to obtain corrected dynamic scene data; a construction unit configured to construct an initialization simulation test environment based on the corrected dynamic scene data and the static scene data; a simulation testing unit configured to execute an automatic driving simulation testing operation in the initialization simulation testing environment to generate a simulation testing planning path set; the generating unit is configured to generate a first automatic driving simulation test result in response to determining that each simulation test planning path in the simulation test planning path set meets a preset path condition.
In a third aspect, some embodiments of the present disclosure provide an electronic device, comprising: one or more processors; a storage device, on which one or more programs are stored, which when executed by one or more processors cause the one or more processors to implement the method described in any implementation of the first aspect.
In a fourth aspect, some embodiments of the present disclosure provide a computer readable medium on which a computer program is stored, wherein the program, when executed by a processor, implements the method described in any of the implementations of the first aspect.
The above embodiments of the present disclosure have the following advantages: by the automatic driving simulation test method of some embodiments of the present disclosure, the accuracy of the test result can be improved. Specifically, the reason for the reduced accuracy of the test results is that: the off-line test mode is difficult to analyze aiming at the current vehicle and dynamic obstacle vehicle interaction scene, so that the test is difficult to be carried out comprehensively, and therefore, the accuracy of the test result in the interaction aspect is low. Based on this, in the automatic driving simulation test method according to some embodiments of the present disclosure, first, in response to receiving a functional test instruction for an automatic driving path planning module, simulation test scenario data corresponding to the functional test instruction is obtained, where the simulation test scenario data includes static scenario data and dynamic scenario data. By acquiring the simulation test scene data, the simulation test can be performed based on the actual vehicle data in the simulation test scene, so that the large difference between the simulation test environment and the real environment is avoided. Meanwhile, the simulation test scene data is divided into static scene data and dynamic scene data, and the method can be used for constructing a simulation test environment with fine granularity. And then, performing off-line correction processing on the dynamic scene data included in the simulation test scene data to obtain corrected dynamic scene data. Through the off-line correction processing, the off-line testing mode can be integrated into the simulation testing mode. Therefore, the accuracy of dynamic scene data in the simulation test data is improved. And then, establishing an initialization simulation test environment based on the corrected dynamic scene data and the static scene data. In this case, the off-line testing method is integrated to improve the accuracy of the dynamic scene data in the simulation test data, so that the difference between the simulation environment and the real environment can be reduced to a certain extent. Therefore, the authenticity of the constructed initialization simulation test environment is improved. And then, executing the automatic driving simulation test operation in the initialization simulation test environment to generate a simulation test planning path set. In order to improve the test comprehensiveness, therefore, a plurality of simulation test planning paths are generated in the simulation test. And finally, generating a first automatic driving simulation test result in response to the fact that all the simulation test planning paths in the simulation test planning path set meet the preset path conditions. By introducing the preset path condition, the accuracy of each simulation test planning path can be further improved. Thus, the accuracy of the test results can be further improved.
Drawings
The above and other features, advantages, and aspects of embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It should be understood that the drawings are schematic and that elements and components are not necessarily drawn to scale.
FIG. 1 is a flow diagram of some embodiments of an automated driving simulation testing method according to the present disclosure;
FIG. 2 is a schematic structural diagram of some embodiments of an automated driving simulation test apparatus according to the present disclosure;
FIG. 3 is a schematic block diagram of an electronic device suitable for use in implementing some embodiments of the present disclosure.
Detailed Description
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.
It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings. The embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict.
It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence of the functions performed by the devices, modules or units.
It is noted that references to "a" or "an" in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will appreciate that references to "one or more" are intended to be exemplary and not limiting unless the context clearly indicates otherwise.
The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.
The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
Fig. 1 illustrates a flow 100 of some embodiments of an automated driving simulation testing method according to the present disclosure. The automatic driving simulation test method comprises the following steps:
step 101, in response to receiving a functional test instruction for the automatic driving path planning module, acquiring simulation test scene data corresponding to the functional test instruction.
In some embodiments, in response to receiving a functional test instruction for the automatic driving path planning module, an execution subject of the automatic driving simulation test method may obtain, in a wired manner or in a wireless manner, simulation test scenario data corresponding to the functional test instruction. The simulation test scenario data may include static scenario data and dynamic scenario data. Secondly, the automatic driving path planning module can be a function to be tested in the simulation test. The functional test instruction can be used for representing that the function of the automatic driving path planning module has larger risk errors and needs to be tested. The static scene data may be static data detected by a vehicle sensing device (e.g., a laser radar) or a vision device (e.g., a camera) during actual movement of the current vehicle, such as lane line coordinates, street lamp coordinates, lamp post coordinates, and the like. The dynamic scene data may include current vehicle data and obstacle vehicle data within a certain range around the current vehicle. For example, current vehicle size information, current vehicle speed value, obstacle vehicle speed value, and the like.
It is noted that the wireless connection means may include, but is not limited to, a 3G/4G connection, a WiFi connection, a bluetooth connection, a WiMAX connection, a Zigbee connection, a UWB (ultra wideband) connection, and other wireless connection means now known or developed in the future.
In some optional implementation manners of some embodiments, the obtaining, by the execution main body, simulation test scenario data corresponding to the functional test instruction may include:
firstly, determining a test time point corresponding to the functional test instruction. The test time point may be a time point at which the functional test instruction is generated.
And secondly, acquiring simulation test scene data corresponding to the target time point. The target time point may be a time point which is separated from the test time point by a preset test time period (for example, 5 seconds). Here, the simulation test scenario data corresponding to the target time point may be scenario data at a time point within a certain time interval (e.g., 3 seconds or 10 frames, etc.) of the target time point. And the time point when the function test instruction is received is the time point when the automatic driving path planning module has problems. Therefore, it is necessary to acquire simulated test scenario data before the test time point. Thus, testing of problematic portions of the autopilot path planning module may be facilitated. In addition, the simulation test scenario data may be data in the actual moving process of the current vehicle.
And 102, performing offline correction processing on dynamic scene data included in the simulation test scene data to obtain corrected dynamic scene data.
In some embodiments, the execution subject may perform offline correction processing on dynamic scene data included in the simulation test scene data to obtain corrected dynamic scene data.
In some optional implementations of some embodiments, the dynamic scene data further includes current vehicle size information, a current vehicle relative pose matrix sequence, an obstacle vehicle size information set, and an obstacle vehicle relative pose matrix set, and a current vehicle position coordinate and an obstacle vehicle position coordinate set corresponding to the target time point. The executing step of performing offline correction processing on the dynamic scene data included in the simulation test scene data by the executing step to obtain corrected dynamic scene data may include the following steps:
firstly, extracting static scene information from the static scene data to obtain a static characteristic corner point image coordinate set sequence and a static characteristic map coordinate set. Each static feature corner point image coordinate set in the static feature corner point image coordinate set sequence may be a road image detection result of each frame from a time point a certain time interval before the target time point to a time point a certain time interval after the target time point. Therefore, each static feature corner image coordinate in each static feature corner image coordinate set may be a two-dimensional coordinate in the same image coordinate system corresponding to the same time instant. Each static feature map coordinate in the set of static feature map coordinates may be three-dimensional coordinates in the same map coordinate system. The current vehicle size information may include a length value, a width value, etc. of the current vehicle. The current vehicle relative pose matrix sequence can be used for representing the relative position and pose of the current vehicle of each frame between a time point which is a certain time interval before the target time point and a time point which is a certain time interval after the target time point. The relative pose matrix may be a transformation matrix of the body coordinate system of the current vehicle relative to the map coordinate system. Each obstacle vehicle size information in the set of obstacle vehicle size information may correspond to an obstacle vehicle. Each obstacle vehicle size information may include an obstacle vehicle length value, an obstacle vehicle width value, and the like. Each obstacle vehicle relative pose matrix in the obstacle vehicle relative pose matrix set may correspond to an obstacle vehicle to characterize a position pose of the obstacle vehicle at the target time point. Therefore, each current vehicle relative pose matrix can correspond to each static feature corner point image coordinate set in the static feature corner point image coordinate set sequence one by one. And secondly, static scene information extraction is carried out on the static scene data through a preset static feature extraction algorithm to obtain a static feature corner point image coordinate set and a static feature map coordinate set. The image coordinate system may be an image coordinate system of a road image captured by the onboard camera at the target time point. The map coordinate system may be a map coordinate system of a preset high-precision map.
As an example, the above-described static feature extraction algorithm may include, but is not limited to, at least one of: SIFT (Scale-invariant Feature Transform) algorithm, surf (Speeded Up Robust Features) algorithm, harris corner detection, FAST corner detection, BRIEF (Binary Robust Independent elements Features), and the like.
And secondly, correcting the relative position and orientation matrix of the current vehicle corresponding to the target time point in the relative position and orientation matrix sequence of the current vehicle based on the relative position and orientation matrix sequence of the current vehicle, the coordinate set sequence of the static characteristic angular point image and the coordinate set of the static characteristic map to obtain a corrected relative position and orientation matrix. First, a detection covariance matrix corresponding to each static feature corner point image coordinate in each static feature corner point image coordinate set in the static feature corner point image coordinate set sequence may be obtained. The detection covariance matrix may be generated when detecting the coordinates of the corner image. Next, a relative covariance matrix (dimension may be 6 × 6) of a special euclidean group corresponding to each adjacent current vehicle relative pose matrix in the above-described current vehicle relative pose matrix sequence may be acquired. Here, the detection covariance matrix may be a 2 × 2 matrix. Then, the current vehicle relative pose matrix sequence corresponding to the target time point in the current vehicle relative pose matrix sequence may be corrected by the following formula:
Figure DEST_PATH_IMAGE001
wherein,
Figure 582627DEST_PATH_IMAGE002
a matrix is represented.
Figure DEST_PATH_IMAGE003
And representing the corrected relative pose matrix.
Figure 840433DEST_PATH_IMAGE004
Figure DEST_PATH_IMAGE005
Figure 863753DEST_PATH_IMAGE006
Representing preset weight coefficients. May both be set to 1.
Figure DEST_PATH_IMAGE007
Representing optimization objectivesNamely, the current vehicle relative pose matrix corresponding to the target time point in the current vehicle relative pose matrix sequence.
Figure 839799DEST_PATH_IMAGE008
Representing the minimization objective function. E denotes an error value.
Figure DEST_PATH_IMAGE009
Figure 849343DEST_PATH_IMAGE010
Figure DEST_PATH_IMAGE011
The method is used for shortening the formula length and has no specific meaning.
Figure 86290DEST_PATH_IMAGE012
Figure DEST_PATH_IMAGE013
Figure 155877DEST_PATH_IMAGE014
Indicating a serial number.
Figure DEST_PATH_IMAGE015
Indicating that the coordinates in brackets are projected to the image coordinate system.
Figure 619219DEST_PATH_IMAGE016
And representing the relative position and orientation matrix sequence of the current vehicle and the relative position and orientation matrix of the current vehicle corresponding to the static characteristic corner point image coordinate set in the static characteristic corner point image coordinate set sequence.
Figure DEST_PATH_IMAGE017
Representing the relative position and orientation matrix sequence of the current vehicle and the first in the static characteristic corner point image coordinate set sequence
Figure 25930DEST_PATH_IMAGE013
Current corresponding to image coordinate set of static feature corner pointAnd (5) vehicle relative pose matrixes.
Figure 523907DEST_PATH_IMAGE018
Representing an inversion matrix.
Figure DEST_PATH_IMAGE019
Representing the static feature map coordinates in the set of static feature map coordinates.
Figure 889029DEST_PATH_IMAGE020
The second in the map coordinate set representing the static feature
Figure 574089DEST_PATH_IMAGE012
Static feature map coordinates.
Figure DEST_PATH_IMAGE021
Representing the coordinates of the static feature corner image in a sequence of sets of static feature corner image coordinates.
Figure 191015DEST_PATH_IMAGE022
The first in the coordinate set sequence of the image representing the corner point of the static feature
Figure 277919DEST_PATH_IMAGE013
The first in the image coordinate set of static feature corner points
Figure 220468DEST_PATH_IMAGE014
And (5) image coordinates of the static feature corner points.
Figure DEST_PATH_IMAGE023
A covariance matrix is represented.
Figure 251878DEST_PATH_IMAGE024
Is shown to correspond to the above
Figure 406915DEST_PATH_IMAGE022
Detecting the covariance matrix.
Figure DEST_PATH_IMAGE025
Showing the mahalanobis distance.
Figure 613906DEST_PATH_IMAGE026
The method represents a preset logarithmic mapping function and can represent the function mapping relation between a special Euclidean group and a Lialgebraic Euclidean group.
Figure DEST_PATH_IMAGE027
Representing the relative position and orientation matrix sequence of the current vehicle and the first in the static characteristic corner point image coordinate set sequence
Figure 320831DEST_PATH_IMAGE028
And the current vehicle relative pose matrix corresponds to the static characteristic corner point image coordinate set.
Figure DEST_PATH_IMAGE029
Is shown as
Figure 980482DEST_PATH_IMAGE013
The relative position matrix of the current vehicle corresponding to the image coordinate set of the static characteristic corner points is relative to the first position matrix
Figure 939211DEST_PATH_IMAGE028
And (4) a transformation matrix of the relative pose matrix of the current vehicle corresponding to the static characteristic corner point image coordinate set.
Figure 708DEST_PATH_IMAGE030
Indicating a pre-measured
Figure 144113DEST_PATH_IMAGE013
The relative position matrix of the current vehicle corresponding to the image coordinate set of the static characteristic corner points is relative to the first position matrix
Figure 291061DEST_PATH_IMAGE028
And the transformation matrix of the relative pose matrix of the current vehicle corresponding to the static characteristic corner point image coordinate set.
Figure DEST_PATH_IMAGE031
Is shown to correspond toThe first in the relative position and posture matrix sequence of the front vehicle
Figure 53480DEST_PATH_IMAGE013
Is first and second
Figure 969484DEST_PATH_IMAGE028
A relative covariance matrix of the current vehicle relative pose matrix.
Figure 18211DEST_PATH_IMAGE032
And representing a preset transformation matrix corresponding to the optimization objective.
Figure DEST_PATH_IMAGE033
A relative covariance matrix corresponding to the optimization objective described above is represented.
And thirdly, determining the corrected relative pose matrix and the obstacle vehicle relative pose matrix set as corrected dynamic scene data.
And 103, constructing an initialization simulation test environment based on the corrected dynamic scene data and the corrected static scene data.
In some embodiments, the execution subject may construct an initialization simulation test environment based on the corrected dynamic scenario data and the static scenario data.
In some optional implementation manners of some embodiments, the constructing an initialization simulation test environment by the execution main body based on the corrected dynamic scene data and the static scene data may include:
firstly, fusing the static scene data to a test scene to be filled to obtain a static test environment. The test scene to be filled may be generated by a preset scene construction method. The test scene to be filled is in the map coordinate system. The fusion may be to convert each coordinate included in the static scene data into a map coordinate system in the test scene to be filled, so as to obtain the static test environment.
As an example, the scene construction method may be a uniform engine.
And secondly, constructing a current vehicle test model and an obstacle vehicle test model set in the static test environment based on the current vehicle size information, the obstacle vehicle size information set, the corrected relative pose matrix, the obstacle vehicle position coordinate set and the current vehicle position coordinate. The current vehicle size information, the set of obstacle vehicle size information, the corrected relative pose matrix, the set of obstacle vehicle position coordinates, and the current vehicle position coordinates may be input to the phantom engine to construct a current vehicle test model and a set of obstacle vehicle test models. In practice, building a static test scenario may characterize the actual scenario used for simulation testing. And adding the current vehicle test model and the obstacle vehicle test model set can be used for simulating the current vehicle and the obstacle vehicle in a static test scene.
Thirdly, performing attitude adjustment on each obstacle vehicle test model in the obstacle vehicle test model set by using the corrected relative attitude matrix and the obstacle vehicle relative attitude matrix set, and determining the static test environment after the attitude adjustment as an initialized simulation test environment. And the relative pose matrix of each obstacle vehicle in the relative pose matrix set of the obstacle vehicles is the pose matrix of the obstacle vehicle relative to the current vehicle. Therefore, after the pose matrix of the current vehicle is corrected, the relative pose matrix of each obstacle vehicle can be adjusted at the same time. The obstacle vehicle test model is corrected in this way, and the position and the posture of the obstacle vehicle test model relative to the current vehicle simulation test model in a static simulation test scene are corrected. Therefore, the simulation test scene can be further close to the actual traffic scene. Thus, it can be used to improve the accuracy of the simulation test results.
And 104, executing the automatic driving simulation test operation in the initialization simulation test environment to generate a simulation test planning path set.
In some embodiments, the execution subject may execute an automated driving simulation test operation in the initialization simulation test environment to generate a set of simulation test plan paths.
In some optional implementations of some embodiments, the executing body executing an automated driving simulation test operation in the initialization simulation test environment to generate a simulation test planning path set may include the following steps:
the method comprises the steps of firstly, determining the acceleration value and the acceleration change rate of each obstacle vehicle test model in the current vehicle test model and the obstacle vehicle test model set in a target time period, and obtaining the current vehicle acceleration value, the current vehicle acceleration change rate, the obstacle vehicle acceleration value set and the obstacle vehicle acceleration change rate set. The target time period may be a time period within a certain time interval from the target time point.
And secondly, executing the following simulation test steps based on the preset simulation test times to generate a simulation test planning path set:
and a first substep of predicting the track of each obstacle vehicle test model in the obstacle vehicle test model set in the initialization simulation test environment based on the obstacle vehicle acceleration value set and the obstacle vehicle acceleration change rate set to obtain an obstacle vehicle predicted track set. The number of simulation tests may be used to limit the number of simulation test cycles executed. Therefore, different obstacle vehicle movement conditions are covered with great probability through the cycle test. Furthermore, the result of the simulation test has higher accuracy.
And a second substep of sending the current vehicle position coordinate, the current vehicle acceleration value, the current vehicle acceleration change rate and the set of predicted obstacle vehicle trajectories to the automatic driving path planning module for planning the current vehicle trajectory to obtain a simulation test planned path. The automatic driving path planning module can perform path planning by using the received current vehicle position coordinate, the received current vehicle acceleration value, the received current vehicle acceleration change rate and the received obstacle vehicle predicted path set to generate a simulation test planning path. Specifically, the process of planning the path by the automatic driving path planning module in the simulation test is not executed in the initialization simulation test environment. In addition, although the path planning is not executed in the initialization simulation test environment, the current vehicle test model and each obstacle vehicle test model in the initialization simulation test environment respectively perform simulation movement according to the generated simulation test planning path and the obstacle vehicle predicted track. Meanwhile, the movement data and traffic risk identifications of the current vehicle test model and each obstacle vehicle test model are recorded. For example, the movement data may include distance values between the current vehicle test model and each obstacle vehicle test model, velocity values, acceleration values of the current vehicle test model, velocity values, acceleration values of each obstacle vehicle test model, and the like. Here, the traffic risk identification may be used to characterize whether a traffic risk exists for the current vehicle. E.g. collision risk, etc.
And a third substep, adding the simulation test planning path to an initial planning path set, and determining the number of paths of the initial planning path in the added initial planning path set.
And a fourth substep of determining the initial planned path set as a simulation test planned path set in response to determining that the number of paths is equal to the number of simulation tests.
Optionally, the simulation testing step may further include the following steps:
and executing the simulation test step again in response to determining that the number of paths is less than the simulation test times.
The above formula and its related content are used as an invention point of the embodiment of the present disclosure, and can further solve the technical problem mentioned in the background art that "the off-line testing mode is difficult to analyze for the current vehicle and dynamic obstacle vehicle interaction scene, so that it is difficult to perform a complete test, and thus the accuracy of the test result in the interaction aspect is low, and meanwhile, the commonly used simulation testing method is to use real vehicle data, so that there is a difference between the simulation data and the actual data, and thus, there is a great difference between the simulation environment and the real environment, and thus, both the off-line testing and the commonly used simulation testing do not meet the requirement of the automatic driving function testing, and further, the accuracy of the test result is reduced". Firstly, through static scene information extraction, a static feature corner point image coordinate set sequence and a static feature map coordinate set for participating in simulation test can be extracted from simulation test scene data before and after a target time point. Therefore, the construction of the simulation test environment can be facilitated. Secondly, by the formula, the relative position matrix of the current vehicle corresponding to the target time point can be corrected by using the coordinates of each static characteristic corner point image, the coordinates of the static characteristic corner point image and other data. Therefore, the accuracy of converting the current vehicle actual data into the simulation test scenario can be improved. And the accuracy of the relative pose matrix of the current vehicle corresponding to the target time point is improved, so that the data of other obstacle vehicles can be synchronously adjusted. Therefore, each obstacle vehicle test model in the simulation test environment is corrected. The position posture of the static simulation test scene relative to the current vehicle simulation test model is more accurate. Therefore, the simulation test scene can be further close to the actual traffic scene. Therefore, the problem that the simulation environment is different from the real environment in a large degree can be avoided to the greatest extent. Furthermore, the method can be used for improving the accuracy of the simulation test result.
And 105, generating a first automatic driving simulation test result in response to the fact that all the simulation test planning paths in the simulation test planning path set meet the preset path conditions.
In some embodiments, the execution subject may generate a first autopilot simulation test result in response to determining that each of the simulation test planned paths in the set of simulation test planned paths satisfies a preset path condition. The preset path condition may be that no traffic risk identifier exists in the movement data recorded in the initialized simulation test environment. In practice, the preset path condition may further include that the similarity between each simulation test planned path and the preset planned path is greater than a preset threshold (for example, 98%), and the like. Here, each simulation test planned path in the simulation test planned path set meets a preset path condition, and the test of the automatic driving path planning module can be represented to be qualified. Thus, the generated first autopilot simulation test result may be information that characterizes the eligibility of the autopilot path planning module test.
Optionally, the executing body may further execute the following steps:
and in the first step, a second automatic driving simulation test result is generated in response to the fact that the simulation test planning paths which do not meet the preset path condition exist in the simulation test planning path set. The second automatic driving simulation test result can represent that the automatic driving path planning module is unqualified in test.
And secondly, sending the first automatic driving simulation test result or the second automatic driving simulation test result to a test display terminal for displaying.
The above embodiments of the present disclosure have the following advantages: by the automatic driving simulation test method of some embodiments of the present disclosure, the accuracy of the test result can be improved. Specifically, the reason for the reduced accuracy of the test results is that: the off-line test mode is difficult to analyze aiming at the current vehicle and dynamic obstacle vehicle interaction scene, so that the test is difficult to be carried out comprehensively, and therefore, the accuracy of the test result in the interaction aspect is low. Based on this, in the automatic driving simulation test method according to some embodiments of the present disclosure, first, in response to receiving a functional test instruction for an automatic driving path planning module, simulation test scenario data corresponding to the functional test instruction is obtained, where the simulation test scenario data includes static scenario data and dynamic scenario data. By acquiring the simulation test scene data, the simulation test can be performed based on the actual vehicle data in the simulation test scene, so that the large difference between the simulation test environment and the real environment is avoided. Meanwhile, the simulation test scene data is divided into static scene data and dynamic scene data, and the method can be used for constructing a simulation test environment with fine granularity. And then, performing off-line correction processing on the dynamic scene data included in the simulation test scene data to obtain corrected dynamic scene data. Through the off-line correction processing, the off-line testing mode can be integrated into the simulation testing mode. Therefore, the accuracy of dynamic scene data in the simulation test data is improved. And then, establishing an initialization simulation test environment based on the corrected dynamic scene data and the static scene data. In this case, the off-line testing method is integrated to improve the accuracy of the dynamic scene data in the simulation test data, so that the difference between the simulation environment and the real environment can be reduced to a certain extent. Therefore, the authenticity of the constructed initialization simulation test environment is improved. And finally, executing the automatic driving simulation test operation in the initialization simulation test environment to generate a simulation test planning path set. In order to improve the test comprehensiveness, a plurality of simulation test planning paths are generated in the simulation test. And finally, generating a first automatic driving simulation test result in response to the fact that all the simulation test planning paths in the simulation test planning path set meet the preset path conditions. By introducing the preset path condition, the accuracy of each simulation test planning path can be further improved. Thus, the accuracy of the test result can be further improved.
With further reference to fig. 2, as an implementation of the methods illustrated in the above figures, the present disclosure provides some embodiments of an automated driving simulation test apparatus, which correspond to those of the method embodiments illustrated in fig. 1, and which may be particularly applicable in various electronic devices.
As shown in fig. 2, the automated driving simulation test apparatus 200 of some embodiments includes: the device comprises an acquisition unit 201, a rectification processing unit 202, a construction unit 203, a simulation testing unit 204 and a generation unit 205. The obtaining unit 201 is configured to, in response to receiving a functional test instruction for an automatic driving path planning module, obtain simulation test scenario data corresponding to the functional test instruction, where the simulation test scenario data includes static scenario data and dynamic scenario data; a correction processing unit 202, configured to perform offline correction processing on the dynamic scene data included in the simulation test scene data, so as to obtain corrected dynamic scene data; a constructing unit 203 configured to construct an initialization simulation test environment based on the corrected dynamic scene data and the static scene data; a simulation testing unit 204 configured to execute an automatic driving simulation testing operation in the initialization simulation testing environment to generate a simulation testing planning path set; the generating unit 205 is configured to generate a first autopilot simulation test result in response to determining that each of the set of simulation test planned paths satisfies a preset path condition.
It will be understood that the units described in the apparatus 200 correspond to the various steps in the method described with reference to fig. 1. Thus, the operations, features and resulting advantages described above with respect to the method are also applicable to the apparatus 200 and the units included therein, and are not described herein again.
Referring now to fig. 3, a block diagram of an electronic device 300 suitable for use in implementing some embodiments of the present disclosure is shown. The electronic device shown in fig. 3 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
As shown in fig. 3, the electronic device 300 may include a processing means 301 (e.g., a central processing unit, a graphics processor, etc.) that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM) 302 or a program loaded from a storage means 308 into a Random Access Memory (RAM) 303. In the RAM 303, various programs and data necessary for the operation of the electronic apparatus 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input/output (I/O) interface 305 is also connected to bus 304.
Generally, the following devices may be connected to the I/O interface 305: input devices 306 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; an output device 307 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage devices 308 including, for example, magnetic tape, hard disk, etc.; and a communication device 309. The communication means 309 may allow the electronic device 300 to communicate wirelessly or by wire with other devices to exchange data. While fig. 3 illustrates an electronic device 300 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided. Each block shown in fig. 3 may represent one device or may represent multiple devices, as desired.
In particular, according to some embodiments of the present disclosure, the processes described above with reference to the flow diagrams may be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer-readable medium, the computer program comprising program code for performing the method illustrated by the flow chart. In some such embodiments, the computer program may be downloaded and installed from a network through the communication device 309, or installed from the storage device 308, or installed from the ROM 302. The computer program, when executed by the processing apparatus 301, performs the above-described functions defined in the methods of some embodiments of the present disclosure.
It should be noted that the computer readable medium described above in some embodiments of the present disclosure may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In some embodiments of the disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In some embodiments of the present disclosure, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
In some embodiments, the clients, servers may communicate using any currently known or future developed network Protocol, such as HTTP (Hyper Text Transfer Protocol), and may interconnect with any form or medium of digital data communication (e.g., a communications network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network.
The computer readable medium may be embodied in the apparatus; or may exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: responding to a received function test instruction aiming at an automatic driving path planning module, and acquiring simulation test scene data corresponding to the function test instruction, wherein the simulation test scene data comprises static scene data and dynamic scene data; off-line correction processing is carried out on dynamic scene data included in the simulation test scene data to obtain corrected dynamic scene data; establishing an initialization simulation test environment based on the corrected dynamic scene data and the static scene data; executing an automatic driving simulation test operation in the initialization simulation test environment to generate a simulation test planning path set; and generating a first automatic driving simulation test result in response to the fact that all the simulation test planning paths in the simulation test planning path set meet the preset path conditions.
Computer program code for carrying out operations for embodiments of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in some embodiments of the present disclosure may be implemented by software or hardware. The described units may also be provided in a processor, and may be described as: a processor includes an acquisition unit, a correction processing unit, a construction unit, a simulation test unit, and a generation unit. The names of these units do not in some cases constitute a limitation to the unit itself, and for example, the acquiring unit may also be described as a "unit that acquires simulation test scenario data corresponding to a functional test instruction".
The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems on a chip (SOCs), complex Programmable Logic Devices (CPLDs), and the like.
The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combination of the above-mentioned features, but also encompasses other embodiments in which any combination of the above-mentioned features or their equivalents is made without departing from the inventive concept as defined above. For example, the above features and (but not limited to) the features with similar functions disclosed in the embodiments of the present disclosure are mutually replaced to form the technical solution.

Claims (10)

1. An automated driving simulation test method, comprising:
responding to a received function test instruction aiming at an automatic driving path planning module, and acquiring simulation test scene data corresponding to the function test instruction, wherein the simulation test scene data comprises static scene data and dynamic scene data;
off-line correction processing is carried out on dynamic scene data included in the simulation test scene data to obtain corrected dynamic scene data;
establishing an initialization simulation test environment based on the corrected dynamic scene data and the static scene data;
executing automatic driving simulation test operation in the initialization simulation test environment to generate a simulation test planning path set;
and generating a first automatic driving simulation test result in response to the fact that all the simulation test planning paths in the simulation test planning path set meet the preset path conditions.
2. The method of claim 1, wherein the method further comprises:
generating a second automatic driving simulation test result in response to determining that the simulation test planning path set which does not meet the preset path condition exists in the simulation test planning path set, wherein the second automatic driving simulation test result represents that the automatic driving path planning module is unqualified in test;
and sending the first automatic driving simulation test result or the second automatic driving simulation test result to a test display terminal for displaying.
3. The method of claim 1, wherein said obtaining simulation test scenario data corresponding to the functional test instruction comprises:
determining a test time point corresponding to the functional test instruction;
and acquiring simulation test scene data corresponding to a target time point, wherein the target time point is a time point which is before the test time point and is separated by a preset test duration.
4. The method of claim 3, wherein the dynamic scene data includes current vehicle size information, a current vehicle relative pose matrix sequence, an obstacle vehicle size information set, and an obstacle vehicle relative pose matrix set, and a current vehicle position coordinate and an obstacle vehicle position coordinate set corresponding to the target time point; and
the off-line correction processing is performed on the dynamic scene data included in the simulation test scene data to obtain corrected dynamic scene data, and the off-line correction processing includes:
extracting static scene information from the static scene data to obtain a static characteristic corner point image coordinate set sequence and a static characteristic map coordinate set;
correcting a current vehicle relative pose matrix corresponding to the target time point in the current vehicle relative pose matrix sequence based on the current vehicle relative pose matrix sequence, the static characteristic corner point image coordinate set sequence and the static characteristic map coordinate set to obtain a corrected relative pose matrix;
and determining the corrected relative pose matrix and the obstacle vehicle relative pose matrix set as corrected dynamic scene data.
5. The method of claim 4, wherein said constructing an initialization simulation test environment based on said rectified dynamic scenario data and said static scenario data comprises:
fusing the static scene data to a test scene to be filled to obtain a static test environment;
constructing a current vehicle test model and a barrier vehicle test model set in the static test environment based on the current vehicle size information, the barrier vehicle size information set, the corrected relative pose matrix, the barrier vehicle position coordinate set and the current vehicle position coordinate;
and performing attitude adjustment on each obstacle vehicle test model in the obstacle vehicle test model set by using the corrected relative attitude matrix and the obstacle vehicle relative attitude matrix set, and determining a static test environment after the attitude adjustment as an initialized simulation test environment.
6. The method of claim 5, wherein said performing an automated driving simulation test operation in said initialization simulation test environment to generate a set of simulated test plan paths comprises:
determining the acceleration value and the acceleration change rate of each obstacle vehicle test model in the current vehicle test model and the obstacle vehicle test model set in a target time period to obtain a current vehicle acceleration value, a current vehicle acceleration change rate, an obstacle vehicle acceleration value set and an obstacle vehicle acceleration change rate set;
based on the preset simulation test times, executing the following simulation test steps to generate a simulation test planning path set:
based on the obstacle vehicle acceleration value set and the obstacle vehicle acceleration rate change set, in the initialization simulation test environment, performing track prediction on each obstacle vehicle test model in the obstacle vehicle test model set to obtain an obstacle vehicle prediction track set;
sending the current vehicle position coordinate, the current vehicle acceleration value, the current vehicle acceleration change rate and the obstacle vehicle predicted track set to the automatic driving path planning module to carry out current vehicle track planning so as to obtain a simulation test planned path;
adding the simulation test planning path to an initial planning path set, and determining the path number of the initial planning path in the added initial planning path set;
in response to determining that the number of paths is equal to the number of simulation tests, determining the initial planned path set as a simulation test planned path set.
7. The method of claim 6, wherein the simulation testing step further comprises:
and executing the simulation test step again in response to determining that the number of paths is less than the simulation test times.
8. An automated driving simulation test apparatus comprising:
the automatic driving path planning system comprises an acquisition unit, a processing unit and a control unit, wherein the acquisition unit is configured to respond to a received functional test instruction aiming at an automatic driving path planning module and acquire simulation test scene data corresponding to the functional test instruction, and the simulation test scene data comprises static scene data and dynamic scene data;
the correction processing unit is configured to perform offline correction processing on dynamic scene data included in the simulation test scene data to obtain corrected dynamic scene data;
a construction unit configured to construct an initialization simulation test environment based on the corrected dynamic scene data and the static scene data;
a simulation testing unit configured to perform an automated driving simulation testing operation in the initialization simulation testing environment to generate a set of simulation testing planned paths;
a generating unit configured to generate a first autopilot simulation test result in response to determining that each simulation test planned path in the set of simulation test planned paths satisfies a preset path condition.
9. An electronic device, comprising:
one or more processors;
a storage device having one or more programs stored thereon,
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method recited in any of claims 1-7.
10. A computer-readable medium, on which a computer program is stored, wherein the computer program, when being executed by a processor, carries out the method according to any one of claims 1-7.
CN202211533256.XA 2022-12-02 2022-12-02 Automatic driving simulation test method, device, equipment and computer readable medium Active CN115616937B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211533256.XA CN115616937B (en) 2022-12-02 2022-12-02 Automatic driving simulation test method, device, equipment and computer readable medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211533256.XA CN115616937B (en) 2022-12-02 2022-12-02 Automatic driving simulation test method, device, equipment and computer readable medium

Publications (2)

Publication Number Publication Date
CN115616937A true CN115616937A (en) 2023-01-17
CN115616937B CN115616937B (en) 2023-04-04

Family

ID=84880013

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211533256.XA Active CN115616937B (en) 2022-12-02 2022-12-02 Automatic driving simulation test method, device, equipment and computer readable medium

Country Status (1)

Country Link
CN (1) CN115616937B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116151045A (en) * 2023-04-21 2023-05-23 中汽研汽车检验中心(天津)有限公司 Vehicle simulation test data accuracy analysis method, device, equipment and medium
CN116597690A (en) * 2023-07-18 2023-08-15 山东高速信息集团有限公司 Highway test scene generation method, equipment and medium for intelligent network-connected automobile
CN116663329A (en) * 2023-07-26 2023-08-29 西安深信科创信息技术有限公司 Automatic driving simulation test scene generation method, device, equipment and storage medium

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2019016341A (en) * 2017-07-10 2019-01-31 アンリツ株式会社 Test system and testing method for on-vehicle application
CN110414098A (en) * 2019-07-12 2019-11-05 北京三快在线科技有限公司 A kind of generation method and device of Simulation Test Environment
CN111324945A (en) * 2020-01-20 2020-06-23 北京百度网讯科技有限公司 Sensor scheme determination method, device, equipment and storage medium
CN112417756A (en) * 2020-11-13 2021-02-26 清华大学苏州汽车研究院(吴江) Interactive simulation test system of automatic driving algorithm
CN112987711A (en) * 2019-11-30 2021-06-18 华为技术有限公司 Optimization method of automatic driving regulation algorithm and simulation testing device
CN113515463A (en) * 2021-09-14 2021-10-19 深圳佑驾创新科技有限公司 Automatic testing method and device, computer equipment and storage medium
CN114167752A (en) * 2021-12-01 2022-03-11 中汽研(天津)汽车工程研究院有限公司 Simulation test method and system device for vehicle active safety system
CN114326667A (en) * 2021-12-23 2022-04-12 清华大学 Unmanned test method for fusion of on-line traffic flow simulation and real road environment
US20220136930A1 (en) * 2020-10-30 2022-05-05 Chang'an University System for testing intelligent vehicles
WO2022162190A1 (en) * 2021-01-29 2022-08-04 Five AI Limited Generating simulation environments for testing av behaviour

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2019016341A (en) * 2017-07-10 2019-01-31 アンリツ株式会社 Test system and testing method for on-vehicle application
CN110414098A (en) * 2019-07-12 2019-11-05 北京三快在线科技有限公司 A kind of generation method and device of Simulation Test Environment
CN112987711A (en) * 2019-11-30 2021-06-18 华为技术有限公司 Optimization method of automatic driving regulation algorithm and simulation testing device
CN111324945A (en) * 2020-01-20 2020-06-23 北京百度网讯科技有限公司 Sensor scheme determination method, device, equipment and storage medium
US20220136930A1 (en) * 2020-10-30 2022-05-05 Chang'an University System for testing intelligent vehicles
CN112417756A (en) * 2020-11-13 2021-02-26 清华大学苏州汽车研究院(吴江) Interactive simulation test system of automatic driving algorithm
WO2022162190A1 (en) * 2021-01-29 2022-08-04 Five AI Limited Generating simulation environments for testing av behaviour
CN113515463A (en) * 2021-09-14 2021-10-19 深圳佑驾创新科技有限公司 Automatic testing method and device, computer equipment and storage medium
CN114167752A (en) * 2021-12-01 2022-03-11 中汽研(天津)汽车工程研究院有限公司 Simulation test method and system device for vehicle active safety system
CN114326667A (en) * 2021-12-23 2022-04-12 清华大学 Unmanned test method for fusion of on-line traffic flow simulation and real road environment

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
OSAMA HALABI,ET AL.: "Driver Activity Recognition in Virtual Reality Driving Simulation", 《2017 8TH INTERNATIONAL CONFERENCE ON INFORMATION AND COMMUNICATION SYSTEMS (ICICS)》 *
程姜荣: "基于ROS系统的智能车设计", 《中国优秀硕士学位论文全文数据库 (工程科技Ⅱ辑)》 *

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116151045A (en) * 2023-04-21 2023-05-23 中汽研汽车检验中心(天津)有限公司 Vehicle simulation test data accuracy analysis method, device, equipment and medium
CN116151045B (en) * 2023-04-21 2023-08-01 中汽研汽车检验中心(天津)有限公司 Vehicle simulation test data accuracy analysis method, device, equipment and medium
CN116597690A (en) * 2023-07-18 2023-08-15 山东高速信息集团有限公司 Highway test scene generation method, equipment and medium for intelligent network-connected automobile
CN116597690B (en) * 2023-07-18 2023-10-20 山东高速信息集团有限公司 Highway test scene generation method, equipment and medium for intelligent network-connected automobile
CN116663329A (en) * 2023-07-26 2023-08-29 西安深信科创信息技术有限公司 Automatic driving simulation test scene generation method, device, equipment and storage medium
CN116663329B (en) * 2023-07-26 2024-03-29 安徽深信科创信息技术有限公司 Automatic driving simulation test scene generation method, device, equipment and storage medium

Also Published As

Publication number Publication date
CN115616937B (en) 2023-04-04

Similar Documents

Publication Publication Date Title
CN109858445B (en) Method and apparatus for generating a model
CN115616937B (en) Automatic driving simulation test method, device, equipment and computer readable medium
CN109145781B (en) Method and apparatus for processing image
CN113607185B (en) Lane line information display method, lane line information display device, electronic device, and computer-readable medium
CN115326099B (en) Local path planning method and device, electronic equipment and computer readable medium
CN112001287A (en) Method and device for generating point cloud information of obstacle, electronic device and medium
CN115167182B (en) Automatic driving simulation test method, device, equipment and computer readable medium
CN115540894B (en) Vehicle trajectory planning method and device, electronic equipment and computer readable medium
CN112598731B (en) Vehicle positioning method and device, electronic equipment and computer readable medium
CN110097600B (en) Method and device for identifying traffic sign
CN110956128A (en) Method, apparatus, electronic device, and medium for generating lane line image
CN111586295B (en) Image generation method and device and electronic equipment
CN111461980B (en) Performance estimation method and device of point cloud stitching algorithm
CN115620264B (en) Vehicle positioning method and device, electronic equipment and computer readable medium
CN111340880A (en) Method and apparatus for generating a predictive model
CN116188887A (en) Attribute recognition pre-training model generation method and attribute recognition model generation method
CN110348374B (en) Vehicle detection method and device, electronic equipment and storage medium
CN110136181B (en) Method and apparatus for generating information
CN114119973A (en) Spatial distance prediction method and system based on image semantic segmentation network
CN116010289B (en) Automatic driving simulation scene test method and device, electronic equipment and readable medium
CN111383337A (en) Method and device for identifying objects
CN111540009A (en) Method, apparatus, electronic device, and medium for generating detection information
CN112597174A (en) Map updating method and device, electronic equipment and computer readable medium
CN110991312A (en) Method, apparatus, electronic device, and medium for generating detection information
CN112815959B (en) Vehicle lane level positioning system, method and device and electronic equipment

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