CN115599700A - Auxiliary driving product testing system and method - Google Patents
Auxiliary driving product testing system and method Download PDFInfo
- Publication number
- CN115599700A CN115599700A CN202211587620.0A CN202211587620A CN115599700A CN 115599700 A CN115599700 A CN 115599700A CN 202211587620 A CN202211587620 A CN 202211587620A CN 115599700 A CN115599700 A CN 115599700A
- Authority
- CN
- China
- Prior art keywords
- module
- scene
- data information
- product test
- virtual
- 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.)
- Pending
Links
- 238000012360 testing method Methods 0.000 title claims abstract description 182
- 238000000034 method Methods 0.000 title abstract description 20
- 238000011156 evaluation Methods 0.000 claims abstract description 204
- 230000008447 perception Effects 0.000 claims abstract description 118
- 238000013075 data extraction Methods 0.000 claims abstract description 36
- 238000004088 simulation Methods 0.000 claims abstract description 33
- 230000004927 fusion Effects 0.000 claims description 23
- 238000012800 visualization Methods 0.000 claims description 15
- 238000002347 injection Methods 0.000 claims description 13
- 239000007924 injection Substances 0.000 claims description 13
- 239000000126 substance Substances 0.000 claims description 8
- 230000001960 triggered effect Effects 0.000 claims description 8
- 238000012986 modification Methods 0.000 claims description 7
- 230000004048 modification Effects 0.000 claims description 7
- 230000001133 acceleration Effects 0.000 claims description 6
- 238000001802 infusion Methods 0.000 claims 1
- 239000000243 solution Substances 0.000 description 7
- 238000001514 detection method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 235000008733 Citrus aurantifolia Nutrition 0.000 description 1
- 235000011941 Tilia x europaea Nutrition 0.000 description 1
- 239000010426 asphalt Substances 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 239000004035 construction material Substances 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 239000004571 lime Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/36—Preventing errors by testing or debugging software
- G06F11/3664—Environments for testing or debugging software
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/36—Preventing errors by testing or debugging software
- G06F11/3668—Software testing
- G06F11/3672—Test management
- G06F11/3692—Test management for test results analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a system and a method for testing a driving assistance product, and relates to the technical field of driving assistance. The system comprises: the system comprises a virtual scene simulation module, a scene data extraction module, a perception data acquisition module, a product test evaluation module and an evaluation report generation module; the virtual scene simulation module is used for constructing a virtual scene for testing an auxiliary driving product; the scene data extraction module is used for extracting scene truth value data information in the virtual scene; the perception data acquisition module is used for acquiring vehicle perception data information acquired by the driving assistance product in the virtual scene; the product test evaluation module is used for comparing the scene truth value data information with the vehicle perception data information to determine a product test evaluation result; the evaluation report generation module is used for generating a product test evaluation report according to the product test evaluation result, so that the test risk and the cost can be reduced.
Description
Technical Field
The invention relates to the technical field of assistant driving, in particular to a system and a method for testing assistant driving products.
Background
With the rapid development of vehicle automatic driving technology, vehicle auxiliary driving is increasingly becoming the most important vehicle function. Various performances of the vehicle driving assistance product need to be tested for many times in the development process. At present, the test means of the vehicle auxiliary driving system is mainly real vehicle test. However, in the real vehicle test, it is difficult to realize the repeatability test on extreme weather scenes, dangerous scenes and difficult-to-recover field scenes, so that the test risk and the cost are high, and meanwhile, the obtained test data is inaccurate.
Disclosure of Invention
The invention provides a system and a method for testing a driver assistance product, which are used for reducing the testing risk and the testing cost and improving the accuracy of testing data.
According to an aspect of the present invention, there is provided a driving assistance product testing system, the system including: the system comprises a virtual scene simulation module, a scene data extraction module, a perception data acquisition module, a product test evaluation module and an evaluation report generation module; wherein the content of the first and second substances,
the virtual scene simulation module is used for constructing a virtual scene for testing the auxiliary driving product;
the scene data extraction module is connected with the virtual scene simulation module and used for extracting scene truth value data information in the virtual scene and sending the scene truth value data information to the product test evaluation module;
the perception data acquisition module is connected with the virtual scene simulation module and used for acquiring vehicle perception data information acquired by the driving assistance product in the virtual scene and sending the vehicle perception data information to the product test evaluation module;
the product test evaluation module is respectively connected with the scene data extraction module and the perception data acquisition module, and is used for receiving the scene truth value data information sent by the scene data extraction module and the vehicle perception data information sent by the perception data acquisition module, comparing the scene truth value data information with the vehicle perception data information according to a key evaluation index, determining a product test evaluation result, and sending the product test evaluation result to the evaluation report generation module;
and the evaluation report generation module is used for receiving the product test evaluation result and generating a product test evaluation report according to the product test evaluation result.
According to another aspect of the present invention, there is provided a driving assistance product testing method, the method including:
constructing a virtual scene for testing an auxiliary driving product through a virtual scene simulation module;
extracting scene truth value data information in the virtual scene through a scene data extraction module, and sending the scene truth value data information to a product test evaluation module;
acquiring vehicle perception data information acquired by the driving assistance product in the virtual scene through a perception data acquisition module, and sending the vehicle perception data information to a product test evaluation module;
receiving, by a product test evaluation module, the scene truth value data information sent by the scene data extraction module and the vehicle perception data information sent by the perception data acquisition module, comparing the scene truth value data information with the vehicle perception data information according to a key evaluation index, determining a product test evaluation result, and sending the product test evaluation result to an evaluation report generation module;
and receiving the product test evaluation result through an evaluation report generation module, and generating a product test evaluation report according to the product test evaluation result.
According to the technical scheme of the embodiment of the invention, the virtual scene for testing the auxiliary driving product is constructed through the virtual scene simulation module. And extracting scene truth value data information in the virtual scene through a scene data extraction module, and sending the scene truth value data information to a product test evaluation module, so that various real data information of the target vehicle in the simulation environment can be obtained. The vehicle perception data information collected by the driving assisting product in the virtual scene is obtained through a perception data obtaining module, and the vehicle perception data information is sent to a product testing and evaluating module, so that all items of perception data information of a target vehicle can be obtained. The scene truth value data information sent by the scene data extraction module and the vehicle perception data information sent by the perception data acquisition module are received through the product test evaluation module, the scene truth value data information and the vehicle perception data information are compared according to key evaluation indexes, a product test evaluation result is determined, and the product test evaluation result is sent to the evaluation report generation module. And receiving the product test evaluation result through an evaluation report generation module, and generating a product test evaluation report according to the product test evaluation result. The auxiliary driving product is tested through the virtual scene, the test risk of testing the real vehicle can be avoided, various scenes can be repeatedly constructed for testing, the test cost is reduced, and meanwhile, the accuracy of test data is improved.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present invention, nor do they necessarily limit the scope of the invention. Other features of the present invention will become apparent from the following description.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic diagram of a system for testing a driver assistance product according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a driving assistance product testing method according to a second embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, 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 derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus 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.
Example one
Fig. 1 is a schematic diagram of a driving assistance product testing system according to an embodiment of the present invention, which is applicable to a product test of a driving assistance product. As shown in fig. 1, the system includes: the system comprises a virtual scene simulation module 101, a scene data extraction module 102, a perception data acquisition module 103, a product test evaluation module 104 and an evaluation report generation module 105.
The virtual scene simulation module 101 is configured to construct a virtual scene for testing an assistant driving product. The scene data extraction module 102 is connected to the virtual scene simulation module 101, and configured to extract scene truth data information in the virtual scene and send the scene truth data information to the product test evaluation module 104. The perception data acquisition module 103 is connected to the virtual scene simulation module 101, and is configured to acquire vehicle perception data information acquired by the driving assistance product in the virtual scene and send the vehicle perception data information to the product test evaluation module 104. The product test evaluation module 104 is connected to the scene data extraction module 102 and the perception data acquisition module 103, and is configured to receive the scene truth value data information sent by the scene data extraction module 102, receive the vehicle perception data information sent by the perception data acquisition module 103, compare the scene truth value data information with the vehicle perception data information according to a key evaluation index, determine a product test evaluation result, and send the product test evaluation result to the evaluation report generation module 105. The evaluation report generation module 105 is configured to receive the product test evaluation result, and generate a product test evaluation report according to the product test evaluation result.
Wherein, in the embodiment of the invention, the vehicle configuring the driving assistance product in the virtual scene is determined as the target vehicle. The scene truth data information may refer to real data information in the virtual scene. For example, the scene truth data information may include parameter information of the target vehicle, various items of data information between the target vehicle and the obstacle, various items of information of the target vehicle in the virtual road, and the like. The vehicle perception data information may refer to various items of perception data information acquired by a target vehicle through a virtual sensor in a virtual scene. For example, the vehicle perception information may include distance information between the target vehicle and the obstacle, lane information where the target vehicle is located, speed limit information acquired by the target vehicle, and the like. The key evaluation index may refer to a key evaluation item focused on by a user or a developer. Illustratively, the key evaluation index includes at least one of a data type matching degree, a missing detection rate, a data accuracy, a longitudinal position of the target vehicle, a lateral position of the target vehicle, a longitudinal speed of the target vehicle, a lateral speed of the target vehicle, a longitudinal acceleration of the target vehicle, and a lateral acceleration of the target vehicle. The product test evaluation result may refer to an evaluation result obtained by testing the driving assistance product. The product test evaluation report may refer to an evaluation report generated according to the product test evaluation result.
In this embodiment of the present invention, the virtual scene simulation module 101 may select general scene simulation software, such as VTD. The format of the virtual scene is not limited, and the constructed virtual scene comprises a perfect sensor Radar, lidar, camera and the like. The scene simulation software can output various data information in the scene. The radar sensor can output original points of a two-dimensional image, the lidar sensor can output three-dimensional original point cloud, and the Camera can output video data under the current field angle. The scene data extraction module 102 supports various board bus requirements, such as CAN, CANFD, flexray, ETH, LIN bus, etc. The perception data acquisition module 103 may be a control device that has downloaded a software perception algorithm.
Specifically, when a developer needs to test a driving assistance product, a virtual scene for testing the driving assistance product is constructed by the virtual scene simulation module 101. Scene truth value data information in the virtual scene is extracted through a scene data extraction module 102 in the system, and the scene truth value data information is sent to a product test evaluation module 104. The perception data acquisition module 103 in the system acquires various vehicle perception data information acquired by the driving assistance product in the virtual scene, and the vehicle perception data information is sent to the product test evaluation module 104. Through the product test evaluation module 104, according to a key evaluation index, comparing the scene truth value data information with the vehicle perception data information to determine a product test evaluation result, and sending the product test evaluation result to the evaluation report generation module 105, so that the evaluation report generation module 105 generates a product test evaluation report according to the product test evaluation result.
Illustratively, the virtual scene simulation module 101 includes at least one of a virtual road configuration unit, a virtual traffic configuration unit, a virtual obstacle configuration unit, a virtual weather configuration unit, and a target vehicle configuration unit; the virtual road configuration unit is used for configuring virtual road information in the virtual scene; the virtual traffic configuration unit is used for configuring virtual traffic information of the running of the target vehicle in the virtual scene; the virtual obstacle configuration unit is used for configuring virtual obstacle information influencing the running of the target vehicle in the virtual scene; the virtual weather configuration unit is used for configuring virtual weather information in the virtual scene; the target vehicle configuration unit is used for configuring vehicle parameter information of the target vehicle.
The virtual road information may include road type information (such as expressway, city expressway, national road, provincial road, etc.) and road lane information (such as single lane, multiple lane, lane width, lane line color, type, width, lane crossing position, house on road side, tree, light pole, traffic signal lamp, traffic speed limit board color, etc.). The virtual traffic information may include construction materials, friction coefficients, etc. of the road, for example, the road surface type may be asphalt or a lime road. The virtual obstacle information includes a plurality of traffic participants (e.g., vehicles, pedestrians, and other obstacles). The number, position, speed, running track and the like of each obstacle can be configured through the virtual obstacle configuration unit. The virtual weather information may include parameter information such as weather, cloud amount, rainfall, snow amount, sun position, and sun illumination. The vehicle parameter information may refer to basic vehicle parameters such as length, width, and height of the target vehicle, a vehicle radar, an installation position of a vehicle-mounted camera, and vehicle power information.
Specifically, the virtual road information in the virtual scene is configured according to the virtual road configuration unit. And configuring virtual traffic information of the running of the target vehicle in the virtual scene according to the virtual traffic configuration unit. And configuring virtual obstacle information influencing the running of the target vehicle in the virtual scene according to the virtual obstacle configuration unit. And configuring virtual weather information in the virtual scene according to a virtual weather configuration unit. And configuring the vehicle parameter information of the target vehicle according to the target vehicle.
Illustratively, the product test evaluation module 104 includes: the device comprises a visualization unit, a data comparison unit and an evaluation index operation unit; wherein the content of the first and second substances,
the visualization unit is used for receiving the video data sent by the injection box and displaying the video data; the data comparison unit is configured to receive the scene truth value data information sent by the scene data extraction module 102, receive the vehicle perception data information sent by the perception data acquisition module 103, and display a comparison result between the scene truth value data information and the vehicle perception data information; the evaluation index operation unit is used for modifying the key evaluation index according to an evaluation index operation instruction triggered by a user, wherein the index modification comprises adding the key evaluation index or deleting the key evaluation index.
Wherein the index modification comprises adding a key evaluation index or deleting a key evaluation index. Specifically, the video data sent by the injection box is received through a visualization unit, and the video data corresponding to the virtual scene can be displayed to a user or a developer in real time. And receiving the scene truth value data information and the vehicle perception data information through a data comparison unit, comparing the scene truth value data information with the vehicle perception data information, and displaying a comparison result to a user or a developer in different colors. And the key evaluation index is subjected to index modification through the evaluation index operation unit according to an evaluation index operation instruction triggered by a user, so that the key evaluation index concerned by the user can be selected.
The data comparison unit is further configured to send the vehicle perception data information to the visualization unit; the visualization unit is also used for displaying the vehicle perception data information in the form of an information frame.
In the embodiment of the invention, the vehicle perception data information can be displayed in real time. Specifically, the vehicle perception data information is sent to the visualization unit through the data comparison unit, and is displayed in the form of an information frame through the visualization unit, so that the vehicle perception data information is more obvious and visual.
Illustratively, the evaluation report generation module 105 includes a report form operation unit; the report form selecting unit is used for determining an evaluation report form according to a report form selecting instruction triggered by a user and generating a product test evaluation report based on the evaluation report form.
Wherein the evaluation report form may include at least one of a graph and a pie chart. Specifically, the report form selection unit may determine the evaluation report form according to a report form selection instruction triggered by a user. Based on the evaluation report form, the report form operation unit may generate a product test evaluation report according to a product test evaluation result.
According to the technical scheme of the embodiment of the invention, the virtual scene for testing the auxiliary driving product is constructed through the virtual scene simulation module. Scene truth value data information in the virtual scene is extracted through a scene data extraction module, and the scene truth value data information is sent to a product test evaluation module, so that various real data information of a target vehicle in a simulation environment can be obtained. The vehicle perception data information collected by the auxiliary driving product in the virtual scene is obtained through a perception data obtaining module, and the vehicle perception data information is sent to a product testing and evaluating module, so that all perception data information of a target vehicle can be obtained. The scene truth value data information sent by the scene data extraction module and the vehicle perception data information sent by the perception data acquisition module are received through a product test evaluation module, the scene truth value data information and the vehicle perception data information are compared according to key evaluation indexes, a product test evaluation result is determined, and the product test evaluation result is sent to an evaluation report generation module. And receiving the product test evaluation result through an evaluation report generation module, and generating a product test evaluation report according to the product test evaluation result. The auxiliary driving product is tested through the virtual scene, the test risk of testing the real vehicle can be avoided, various scenes can be repeatedly constructed for testing, the test cost is reduced, and meanwhile, the accuracy of test data is improved.
On the basis of the above embodiment, the system further comprises an injection cassette module; the injection box module is connected to the virtual scene simulation module 101, and is configured to acquire video data of the virtual scene and send the video data to the product test evaluation module 104, so that the product test evaluation module 104 displays the video data.
Among other things, the injection box module may support injection in different file formats, such as a video file format (. YUV/Bayer/. Mp4/. Mkv) and an original point cloud data format (. Pcap), among others.
Specifically, the injection box module may be connected to the virtual scene simulation module 101, the injection box module may send the video data output by the virtual scene simulation module 101 to the product test evaluation module 104, and the product test evaluation module 104 may display the video data in the virtual scene.
On the basis of the foregoing embodiment, the scene data extraction module 120 is further configured to: determining a sequential format of truth data information corresponding to the product test evaluation module 104; and sorting the scene truth value data information based on the sequential format, and sending the scene truth value data information after sorting to the product test evaluation module 104.
Specifically, the scene data extraction module 102 may determine, in an RDB bus form, a sequential format of truth data information corresponding to the product test evaluation module 104 through an ethernet, and the scene data extraction module 102 sorts the scene truth data information according to the sequential format and sends the scene truth data information sorted by the data information to the product test evaluation module 104, so that the product test evaluation module 104 may read the scene truth data information sorted by the data information.
On the basis of the embodiment, the system further comprises a perception data fusion module; wherein the content of the first and second substances,
the perception data fusion module is connected with the perception data acquisition module 103 and used for receiving the vehicle perception data information sent by the perception data acquisition module 103, fusing the vehicle perception data information acquired by a plurality of sensors in a target vehicle, determining vehicle fusion data information and sending the vehicle fusion data information to the product test evaluation module 104; the product test evaluation module 104 is configured to compare the scene truth value data information with the vehicle fusion data information according to a key evaluation index, and determine a product test evaluation result.
The sensing data fusion module can be a processor for storing a software fusion algorithm program. The vehicle perception data information may refer to various items of perception data information acquired by a target vehicle through a virtual perception sensor in a virtual scene. The vehicle fusion data information may be fusion sensing data information obtained by fusing vehicle sensing data information acquired by a plurality of virtual sensing sensors.
According to the technical scheme of the embodiment of the invention, in the configuration process of the virtual scene, various virtual sensing sensors can be configured for the target vehicle, and the virtual sensing sensors are used for acquiring various vehicle sensing data information. In the embodiment of the invention, the driving assistance product testing system further comprises a perception data fusion module, which is used for fusing the perception data information of each vehicle collected by the plurality of virtual perception sensors to determine the vehicle fusion data information. The product test evaluation module 104 compares the scene truth value data information with the vehicle fusion data information according to a key evaluation index, so as to determine a product test evaluation result corresponding to the vehicle fusion data information.
Example two
Fig. 2 is a flowchart of a driving assistance product testing method according to a second embodiment of the present invention. As shown in fig. 2, the method includes:
s301, constructing a virtual scene for testing the auxiliary driving product through a virtual scene simulation module.
S302, scene truth value data information in the virtual scene is extracted through a scene data extraction module, and the scene truth value data information is sent to a product test evaluation module.
S303, vehicle perception data information collected by the driving assistance product in the virtual scene is obtained through a perception data obtaining module, and the vehicle perception data information is sent to a product testing and evaluating module.
S304, receiving the scene truth value data information sent by the scene data extraction module and the vehicle perception data information sent by the perception data acquisition module through a product test evaluation module, comparing the scene truth value data information with the vehicle perception data information according to a key evaluation index, determining a product test evaluation result, and sending the product test evaluation result to an evaluation report generation module.
S305, receiving the product test evaluation result through an evaluation report generation module, and generating a product test evaluation report according to the product test evaluation result.
According to the technical scheme of the embodiment of the invention, the virtual scene for testing the auxiliary driving product is constructed through the virtual scene simulation module. Scene truth value data information in the virtual scene is extracted through a scene data extraction module, and the scene truth value data information is sent to a product test evaluation module, so that various real data information of a target vehicle in a simulation environment can be obtained. The vehicle perception data information collected by the auxiliary driving product in the virtual scene is obtained through a perception data obtaining module, and the vehicle perception data information is sent to a product testing and evaluating module, so that all perception data information of a target vehicle can be obtained. The scene truth value data information sent by the scene data extraction module and the vehicle perception data information sent by the perception data acquisition module are received through a product test evaluation module, the scene truth value data information and the vehicle perception data information are compared according to key evaluation indexes, a product test evaluation result is determined, and the product test evaluation result is sent to an evaluation report generation module. And receiving the product test evaluation result through an evaluation report generation module, and generating a product test evaluation report according to the product test evaluation result. The auxiliary driving product is tested through the virtual scene, the test risk of testing the real vehicle can be avoided, various scenes can be repeatedly constructed for testing, the test cost is reduced, and meanwhile, the accuracy of test data is improved.
On the basis of any optional technical scheme, optionally, the driving assistance product testing system further comprises an injection box module; the method for testing the driver assistance product further comprises the following steps: the injection box module is connected with the virtual scene simulation module to acquire the video data of the virtual scene and send the video data to the product test evaluation module so that the product test evaluation module can display the video data.
On the basis of any optional technical scheme of the invention, optionally, the system further comprises a perception data fusion module. The method may further comprise:
the perception data fusion module is connected with the perception data acquisition module, receives the vehicle perception data information sent by the perception data acquisition module, fuses vehicle perception data information acquired by a plurality of sensors in a target vehicle, determines vehicle fusion data information, and sends the vehicle fusion data information to the product test evaluation module; and comparing the scene truth value data information with the vehicle fusion data information through the product test evaluation module according to a key evaluation index to determine a product test evaluation result.
On the basis of any optional technical scheme of the present invention, optionally, the virtual scene simulation module includes at least one of a virtual road configuration unit, a virtual traffic configuration unit, a virtual obstacle configuration unit, a virtual weather configuration unit, and a target vehicle configuration unit. Correspondingly, the method may further include:
configuring virtual road information in the virtual scene through the virtual road configuration unit; configuring virtual traffic information of the running of the target vehicle in the virtual scene through the virtual traffic configuration unit; configuring virtual obstacle information influencing the running of the target vehicle in the virtual scene through the virtual obstacle configuration unit; configuring virtual weather information in the virtual scene through the virtual weather configuration unit; and configuring the vehicle parameter information of the target vehicle through the target vehicle configuration unit.
On the basis of any optional technical scheme of the present invention, optionally, the product test evaluation module includes: the device comprises a visualization unit, a data comparison unit and an evaluation index operation unit. Accordingly, the method further comprises:
receiving the video data sent by the injection box through the visualization unit, and displaying the video data; receiving, by the data comparison unit, the scene truth value data information sent by the scene data extraction module and the vehicle perception data information sent by the perception data acquisition module, and displaying a comparison result between the scene truth value data information and the vehicle perception data information; and modifying the key evaluation indexes according to an evaluation index operation instruction triggered by a user through the evaluation index operation unit, wherein the index modification comprises adding key evaluation indexes or deleting key evaluation indexes.
On the basis of any optional technical solution of the present invention, optionally, the method further includes sending the vehicle perception data information to the visualization unit through the data comparison unit. And displaying the vehicle perception data information in the form of an information frame through the visualization unit.
On the basis of any optional technical solution of the present invention, optionally, the key evaluation index includes at least one of a data type matching degree, a missing detection rate, a data precision, a longitudinal position of the target vehicle, a lateral position of the target vehicle, a longitudinal speed of the target vehicle, a lateral speed of the target vehicle, a longitudinal acceleration of the target vehicle, and a lateral acceleration of the target vehicle.
On the basis of any optional technical scheme of the present invention, optionally, the evaluation report generation module includes a report form operation unit. Accordingly, the method further comprises: and determining an evaluation report form through the report form selection unit according to a report form selection instruction triggered by a user, and generating a product test evaluation report based on the evaluation report form.
On the basis of any optional technical solution of the present invention, optionally, the method further includes:
determining the sequential format of true value data information corresponding to the product test evaluation module through the scene data extraction module;
and sorting the scene truth value data information based on the sequential format, and sending the scene truth value data information after data information sorting to the product test evaluation module.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present invention may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired results of the technical solution of the present invention can be achieved.
The above-described embodiments should not be construed as limiting the scope of the invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A driver-assist product testing system, the system comprising: the system comprises a virtual scene simulation module, a scene data extraction module, a perception data acquisition module, a product test evaluation module and an evaluation report generation module; wherein the content of the first and second substances,
the virtual scene simulation module is used for constructing a virtual scene for testing the auxiliary driving product;
the scene data extraction module is connected with the virtual scene simulation module and used for extracting scene truth value data information in the virtual scene and sending the scene truth value data information to the product test evaluation module;
the perception data acquisition module is connected with the virtual scene simulation module and used for acquiring vehicle perception data information acquired by the driving assistance product in the virtual scene and sending the vehicle perception data information to the product test evaluation module;
the product test evaluation module is respectively connected with the scene data extraction module and the perception data acquisition module, and is used for receiving the scene truth value data information sent by the scene data extraction module and the vehicle perception data information sent by the perception data acquisition module, comparing the scene truth value data information with the vehicle perception data information according to a key evaluation index, determining a product test evaluation result, and sending the product test evaluation result to the evaluation report generation module;
and the evaluation report generation module is used for receiving the product test evaluation result and generating a product test evaluation report according to the product test evaluation result.
2. The system of claim 1, further comprising an infusion cassette module; wherein the content of the first and second substances,
the injection box module is connected with the virtual scene simulation module and used for acquiring video data of the virtual scene and sending the video data to the product test evaluation module so that the product test evaluation module can display the video data.
3. The system of claim 1, further comprising a perceptual data fusion module; wherein the content of the first and second substances,
the perception data fusion module is connected with the perception data acquisition module and used for receiving the vehicle perception data information sent by the perception data acquisition module, fusing the vehicle perception data information acquired by a plurality of sensors in a target vehicle, determining vehicle fusion data information and sending the vehicle fusion data information to the product test evaluation module;
and the product test evaluation module is used for comparing the scene truth value data information with the vehicle fusion data information according to a key evaluation index to determine a product test evaluation result.
4. The system of claim 1, wherein the virtual scene simulation module comprises at least one of a virtual road configuration unit, a virtual traffic configuration unit, a virtual obstacle configuration unit, a virtual weather configuration unit, and a target vehicle configuration unit; wherein the content of the first and second substances,
the virtual road configuration unit is used for configuring virtual road information in the virtual scene;
the virtual traffic configuration unit is used for configuring virtual traffic information of the running of the target vehicle in the virtual scene;
the virtual obstacle configuration unit is used for configuring virtual obstacle information influencing the running of the target vehicle in the virtual scene;
the virtual weather configuration unit is used for configuring virtual weather information in the virtual scene;
the target vehicle configuration unit is used for configuring vehicle parameter information of the target vehicle.
5. The system of claim 1, wherein the product test evaluation module comprises: the system comprises a visualization unit, a data comparison unit and an evaluation index operation unit; wherein, the first and the second end of the pipe are connected with each other,
the visualization unit is used for receiving the video data sent by the injection box and displaying the video data;
the data comparison unit is configured to receive the scene truth value data information sent by the scene data extraction module, receive the vehicle perception data information sent by the perception data acquisition module, and display a comparison result between the scene truth value data information and the vehicle perception data information;
the evaluation index operation unit is used for modifying the key evaluation index according to an evaluation index operation instruction triggered by a user, wherein the index modification comprises adding the key evaluation index or deleting the key evaluation index.
6. The system of claim 5, wherein the data comparison unit is further configured to send the vehicle awareness data information to the visualization unit;
the visualization unit is also used for displaying the vehicle perception data information in the form of an information frame.
7. The system of claim 5, wherein the key evaluation indicators comprise at least one of a data type match, a miss rate, a data accuracy, a longitudinal position of the target vehicle, a lateral position of the target vehicle, a longitudinal velocity of the target vehicle, a lateral velocity of the target vehicle, a longitudinal acceleration of the target vehicle, and a lateral acceleration of the target vehicle.
8. The system of claim 1, wherein the evaluation report generation module comprises a report form operation unit; wherein the content of the first and second substances,
and the report form selection unit is used for determining an evaluation report form according to a report form selection instruction triggered by a user and generating a product test evaluation report based on the evaluation report form.
9. The system of claim 1, wherein the scene data extraction module is further configured to:
determining the sequential format of true value data information corresponding to the product test evaluation module;
and sorting the scene truth value data information based on the sequential format, and sending the scene truth value data information after sorting to the product test evaluation module.
10. A driving assistance product testing method is applied to a driving assistance product testing system, and comprises the following steps:
constructing a virtual scene for testing an auxiliary driving product through a virtual scene simulation module;
extracting scene truth value data information in the virtual scene through a scene data extraction module, and sending the scene truth value data information to a product test evaluation module;
acquiring vehicle perception data information acquired by the auxiliary driving product in the virtual scene through a perception data acquisition module, and sending the vehicle perception data information to a product test evaluation module;
receiving, by a product test evaluation module, the scene truth value data information sent by the scene data extraction module and the vehicle perception data information sent by the perception data acquisition module, comparing the scene truth value data information with the vehicle perception data information according to a key evaluation index, determining a product test evaluation result, and sending the product test evaluation result to an evaluation report generation module;
and receiving the product test evaluation result through an evaluation report generation module, and generating a product test evaluation report according to the product test evaluation result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211587620.0A CN115599700A (en) | 2022-12-12 | 2022-12-12 | Auxiliary driving product testing system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211587620.0A CN115599700A (en) | 2022-12-12 | 2022-12-12 | Auxiliary driving product testing system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115599700A true CN115599700A (en) | 2023-01-13 |
Family
ID=84851963
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211587620.0A Pending CN115599700A (en) | 2022-12-12 | 2022-12-12 | Auxiliary driving product testing system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115599700A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110779730A (en) * | 2019-08-29 | 2020-02-11 | 浙江零跑科技有限公司 | L3-level automatic driving system testing method based on virtual driving scene vehicle on-ring |
| CN111309600A (en) * | 2020-01-21 | 2020-06-19 | 上汽通用汽车有限公司 | Virtual scene injection automatic driving test method and electronic equipment |
| CN115291515A (en) * | 2022-08-01 | 2022-11-04 | 广州蔚驰科技有限公司 | Automatic driving simulation test system and evaluation method based on digital twinning |
-
2022
- 2022-12-12 CN CN202211587620.0A patent/CN115599700A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110779730A (en) * | 2019-08-29 | 2020-02-11 | 浙江零跑科技有限公司 | L3-level automatic driving system testing method based on virtual driving scene vehicle on-ring |
| CN111309600A (en) * | 2020-01-21 | 2020-06-19 | 上汽通用汽车有限公司 | Virtual scene injection automatic driving test method and electronic equipment |
| CN115291515A (en) * | 2022-08-01 | 2022-11-04 | 广州蔚驰科技有限公司 | Automatic driving simulation test system and evaluation method based on digital twinning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109657355B (en) | Simulation method and system for vehicle road virtual scene | |
| KR102523886B1 (en) | A method and a device for detecting small target | |
| Krämmer et al. | Providentia--A Large-Scale Sensor System for the Assistance of Autonomous Vehicles and Its Evaluation | |
| CN110188482B (en) | Test scene creating method and device based on intelligent driving | |
| CN111179300A (en) | Method, apparatus, system, device and storage medium for obstacle detection | |
| JP2021531462A (en) | Intelligent navigation methods and systems based on topology maps | |
| CN110782120B (en) | Method, system, equipment and medium for evaluating traffic flow model | |
| CN109872530B (en) | Road condition information generation method, vehicle-mounted terminal and server | |
| CN110470311A (en) | A kind of ground drawing generating method, device and computer storage medium | |
| JP5141969B2 (en) | Image recognition apparatus, image recognition program, and point information collection apparatus and navigation apparatus using the same | |
| JP5522475B2 (en) | Navigation device | |
| CN110688943A (en) | Method and device for automatically acquiring image sample based on actual driving data | |
| CN112990293A (en) | Point cloud marking method and device and electronic equipment | |
| CN114639085A (en) | Traffic signal lamp identification method and device, computer equipment and storage medium | |
| Avramović et al. | Real-time large scale traffic sign detection | |
| JP2017130871A (en) | Image generation device for vehicle | |
| CN113253299B (en) | Obstacle detection method, obstacle detection device and storage medium | |
| EP4273501A1 (en) | Method, apparatus, and computer program product for map data generation from probe data imagery | |
| CN115599700A (en) | Auxiliary driving product testing system and method | |
| CN113554871B (en) | Internet of vehicles data processing method and electronic equipment | |
| CN112507887B (en) | Intersection sign extracting and associating method and device | |
| JPH1138154A (en) | Thunder generation predictor | |
| CN115082524A (en) | Vehicle tracking method and system and vehicle | |
| CN115112132A (en) | Perception map generation method and device and computer readable storage medium | |
| CN114241373A (en) | End-to-end vehicle behavior detection method, system, equipment and storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230113 |
|
| RJ01 | Rejection of invention patent application after publication |