CN116822191A - Automatic driving test model construction method, simulation method, equipment and medium - Google Patents
Automatic driving test model construction method, simulation method, equipment and medium Download PDFInfo
- Publication number
- CN116822191A CN116822191A CN202310749603.0A CN202310749603A CN116822191A CN 116822191 A CN116822191 A CN 116822191A CN 202310749603 A CN202310749603 A CN 202310749603A CN 116822191 A CN116822191 A CN 116822191A
- Authority
- CN
- China
- Prior art keywords
- traffic light
- information
- data
- model
- preset
- 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 63
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000004088 simulation Methods 0.000 title claims abstract description 28
- 238000010276 construction Methods 0.000 title claims abstract description 27
- 238000001514 detection method Methods 0.000 claims abstract description 22
- 238000012545 processing Methods 0.000 claims abstract description 16
- 239000000470 constituent Substances 0.000 claims description 18
- 238000005070 sampling Methods 0.000 claims description 13
- 230000000007 visual effect Effects 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000002457 bidirectional effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 125000000174 L-prolyl group Chemical group [H]N1C([H])([H])C([H])([H])C([H])([H])[C@@]1([H])C(*)=O 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Landscapes
- Traffic Control Systems (AREA)
Abstract
The application provides an automatic driving test model construction method, a simulation method, equipment and a medium, wherein the automatic driving test model construction method comprises the following steps: generating semantic information of at least one traffic light in the high-precision map by using the road detection data, and modeling and processing a traffic light infrastructure by using the obtained semantic information of the at least one traffic light to obtain at least one traffic light main body model; acquiring preset state information of at least one traffic light, and adding the preset state information into at least one traffic light main body model to obtain at least one traffic light target model; adding and storing at least one traffic light target model into a high-precision map to realize the construction of an automatic driving test model; according to the scheme, various different traffic light models can be obtained, traffic light standards in actual scenes can be met, manual editing is not needed, and the traffic light model is convenient, quick and high in efficiency.
Description
Technical Field
The application relates to the technical field of automatic driving, in particular to an automatic driving test model construction method, an automatic driving test model simulation method, automatic driving test model simulation equipment and an automatic driving test model medium.
Background
For development of automatic driving technology, road tests can ensure correctness of an automatic driving algorithm and can help find existing problems. The road test comprises an actual road test and a virtual road test. In view of cost and convenience, virtual road testing is mainly used.
In the model for virtual road test, road traffic signals in different areas have similar specifications, but have great differences in patterns, and the switching logic of the road traffic signals is the same as that of an actual scene. The conventional method generally uses art to model a general model of the road traffic signal lamp, but the general model cannot conform to different traffic lamp specifications in an actual scene, and the switching logic needs to be manually edited, so that generalization is difficult.
Disclosure of Invention
The application provides an automatic driving test model construction method, an automatic driving test model simulation method, automatic driving test model simulation equipment and an automatic driving test model simulation medium, so as to solve the problems.
The first aspect of the application provides a method for constructing an automatic driving test model, which comprises the following steps: acquiring road detection data, a corresponding high-precision map and a traffic light foundation structure for test model construction; generating semantic information of at least one traffic light in the high-precision map by using the road detection data; modeling the traffic light infrastructure by utilizing the semantic information of the at least one traffic light to obtain a corresponding at least one traffic light main body model; acquiring preset state information of the at least one traffic light, and adding the preset state information into the at least one traffic light main body model to obtain at least one traffic light target model; and adding and storing the at least one traffic light target model into the high-precision map to realize the construction of an automatic driving test model.
In some embodiments, the traffic light infrastructure includes a base portion and an elevated portion connected to each other; the semantic information of the at least one traffic light includes type information of the at least one traffic light; the modeling processing is performed on the traffic light infrastructure by utilizing the semantic information of the at least one traffic light to obtain a corresponding at least one traffic light main body model, which comprises the following steps: adjusting the elevated part by utilizing the type information and preset specification information of the at least one traffic light to obtain the initial model of the at least one traffic light; and according to the semantic information of the at least one traffic light, performing appearance adding processing on the at least one traffic light initial model to obtain at least one traffic light main body model.
In some embodiments, the base portion and the elevated portion each comprise a plurality of constituent units, wherein the shape of the constituent units is a preset polygonal shape; the semantic information of the at least one traffic light further comprises coordinate information; the processing of appearance addition is performed on the at least one traffic light initial model according to the semantic information of the at least one traffic light to obtain at least one traffic light main body model, and the processing comprises the following steps: generating vertex coordinate data of the constituent units according to the coordinate information; acquiring a preset texture picture, and sampling the preset texture picture by using the type information of the at least one traffic light and the vertex coordinate data to obtain corresponding sampling data; and giving the sampling data to the component units to obtain the at least one traffic light main body model.
In some embodiments, the obtaining the preset texture picture includes: obtaining traffic light appearance data in the road detection data; and cutting the traffic light appearance data to obtain the preset texture picture.
In some embodiments, the traffic light infrastructure further comprises a display portion connected to an end of the elevated portion remote from the base portion; the adding the preset state information to the at least one traffic light body model includes: the preset state information is added to the display portion.
In some embodiments, the adding the preset state information to the display portion further includes: and adding a visual effect to the display part according to the preset specification information.
In some embodiments, the acquiring the preset status information of the at least one traffic light includes: generating traffic light switching sequence data and traffic light switching time data according to the semantic information of the at least one traffic light; generating the preset state information by using the traffic light switching sequence data and the traffic light switching time data; or, acquiring traffic light switching sequence data and traffic light switching time data in the road detection data; and generating the preset state information by using the traffic light switching sequence data and the traffic light switching time data.
The second aspect of the present application provides a simulation method, including: acquiring driving data of an automatic driving vehicle and an automatic driving test model; using the automatic driving test model to simulate the driving data so as to obtain a simulation result; wherein the autopilot test model is derived according to the autopilot test model construction method of the first aspect.
A third aspect of the present application provides an electronic device comprising a memory and a processor coupled to each other, the processor being configured to execute program instructions stored in the memory to implement the autopilot test model construction method of the first aspect or the simulation method of the second aspect.
A fourth aspect of the present application provides a non-transitory computer readable storage medium for storing program instructions which, when executed by a processor, are used to implement the automated driving test model construction method in the first aspect or the simulation method in the second aspect described above.
According to the scheme, the semantic information of at least one traffic light in the high-precision map is generated by utilizing the road detection data, and the traffic light infrastructure is modeled by utilizing the obtained semantic information of the at least one traffic light, so that at least one traffic light main body model can be obtained; acquiring preset state information of at least one traffic light, and adding the preset state information into at least one traffic light main body model to obtain at least one traffic light target model; adding and storing at least one traffic light target model into a high-precision map to realize the construction of an automatic driving test model; according to the scheme, the traffic light basic structure is modeled by utilizing the semantic information of at least one traffic light to obtain at least one traffic light main body model, and the preset state information is added into the at least one traffic light main body model to obtain at least one traffic light target model, so that a plurality of different traffic light models can be obtained, traffic light standards in actual scenes can be met, manual editing is not needed, and the traffic light basic structure modeling method is convenient, quick and efficient.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application as claimed.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.
FIG. 1 is a flow chart of an automatic driving test model construction method in an embodiment of the application;
FIG. 2 is a schematic diagram of the structure of the constituent units in the embodiment of the present application;
FIG. 3 is a flow chart of a simulation method in an embodiment of the application;
FIG. 4 is a schematic diagram of an electronic device according to an embodiment of the present application;
fig. 5 is a schematic diagram of a structure of a nonvolatile computer-readable storage medium in an embodiment of the present application.
Detailed Description
The application is described in further detail below with reference to the drawings and examples. It is specifically noted that the following examples are only for illustrating the present application, but do not limit the scope of the present application. Likewise, the following examples are only some, but not all, of the examples of the present application, and all other examples, which a person of ordinary skill in the art would obtain without making any inventive effort, are within the scope of the present application.
Reference in the specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
The term "and/or" is herein merely an association relationship describing an associated object, meaning that there may be three relationships, e.g., a and/or B, may represent: a exists alone, A and B exist together, and B exists alone. In addition, the character "/" herein generally indicates that the front and rear associated objects are an "or" relationship. Further, "a plurality" herein means two or more than two. In addition, the term "at least one" herein means any one of a plurality or any combination of at least two of a plurality, for example, including at least one of A, B, C, and may mean including any one or more elements selected from the group consisting of A, B and C. Furthermore, the terms "first," "second," and "third" in this disclosure are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated.
As described above, in the model for virtual road test, the road traffic signal lamps in different regions have similar specifications, but the patterns have large differences, and the switching logic should be the same as that of the actual scene. The conventional method generally uses art to model a general model of the road traffic signal lamp, but the general model cannot conform to different traffic lamp specifications in an actual scene, and the switching logic needs to be manually edited, so that generalization is difficult.
Therefore, the application provides an automatic driving test model construction method, an automatic driving test model simulation device and a medium, so as to solve the problems.
Referring to fig. 1, fig. 1 is a flow chart of an automatic driving test model construction method according to an embodiment of the application, and it should be noted that the method of the application is not limited to the flow chart shown in fig. 1 if there are substantially the same results. The method can be applied to electronic equipment with functions of calculation and the like, and the electronic equipment can execute the method by receiving data. The electronic device of the present application may be a server, or a system in which a server and a terminal device cooperate with each other. Further, the server may be hardware or software, which is not limited herein. In some possible implementations, the method for constructing the autopilot test model according to the embodiments of the present application may be implemented by a processor calling computer program instructions stored in a memory. As shown in fig. 1, the automatic driving test model construction method includes the steps of:
s11, acquiring road detection data, a corresponding high-precision map and a traffic light infrastructure, wherein the road detection data is used for building a test model.
Road detection data, namely road and environment information acquired in the road test process, are acquired through the equipped sensors.
The sensors include, but are not limited to, image sensors and radar sensors, and image data may be acquired using the image sensors and point cloud data may be acquired using the radar sensors. For example, the sensor is mounted on a mobile device. The mobile device may be an automated mobile device, such as a robot, an autonomous vehicle, or the like.
In some embodiments, the image sensor may be a camera, the radar sensor may be a lidar sensor, such as a mechanical lidar, the radar sensor may also be a millimeter wave radar; in other embodiments, the sensor capable of implementing the related data acquisition function is not particularly limited.
In an application scenario, an autonomous vehicle travels on a road, and road detection data for test model construction is collected by sensors equipped on the autonomous vehicle.
It can be understood that a high-precision map in a corresponding range can be acquired according to the range of the road detection data. The high-precision map comprises map elements such as road shapes, road marks, traffic signs, obstacles and the like, and the precision of the high-precision map can reach the centimeter level. The traffic light infrastructure may be modeled by three-dimensional modeling software, for example, the three-dimensional modeling software may be 3DS Max, maya, rhino, pro/Engineer, solidworks, or any other three-dimensional modeling software that can be implemented, and is not particularly limited.
S12, semantic information of at least one traffic light in the high-precision map is generated by utilizing the road detection data.
The semantic information of at least one traffic light in the high-precision map can be generated by utilizing the road detection data acquired by the sensor. The semantic information of the at least one traffic light is used for carrying out semantic description on the position information and the height information of the at least one traffic light. In other embodiments, the semantic information may also be used to describe other information of the traffic light, which may be implemented, and is not limited specifically.
And S13, modeling the traffic light infrastructure by utilizing semantic information of at least one traffic light to obtain at least one corresponding traffic light main body model.
It can be understood that the semantic information of the at least one traffic light is used for explaining the information of the at least one traffic light, so that the semantic information of the at least one traffic light is utilized to model the traffic light infrastructure, and the corresponding at least one traffic light main body model can be obtained.
For example, the semantic information X of the at least one traffic light comprises semantic information (X1, X2), wherein the semantic information (X1, X2) characterizes the semantic description of the different types of traffic lights, respectively. The traffic light infrastructure is a, which can be understood as a basic general structure. Modeling the traffic light infrastructure A by using semantic information X1 to obtain a corresponding traffic light main body model a1; and modeling the traffic light infrastructure A by using the semantic information X2 to obtain a corresponding traffic light main body model a2. It can be understood that on the basis of the traffic light infrastructure a, the semantic information (X1-Xn) of how many traffic lights are, and how many traffic light body models (a 1-an) can be obtained accordingly.
S14, acquiring preset state information of at least one traffic light, and adding the preset state information into at least one traffic light main body model to obtain at least one traffic light target model.
The preset status information is used to characterize the overall status information of the traffic lamp, including, for example, but not limited to, switching data and switching time. It is understood that the preset state information of different traffic may be different, and the preset state information of at least one traffic light is added to the corresponding at least one traffic light main body model, so that the corresponding at least one traffic light target model can be obtained.
And S15, adding and storing at least one traffic light target model into the high-precision map so as to construct an automatic driving test model.
After at least one traffic light target model is obtained, adding and storing the at least one traffic light target model into a high-precision map to obtain an automatic driving test model, thereby realizing the construction of the automatic driving test model. Further, the obtained automatic driving test model can be utilized to carry out virtual simulation test on the driving behavior of the automatic driving vehicle.
According to the scheme, the semantic information of at least one traffic light in the high-precision map is generated by utilizing the road detection data, and the traffic light infrastructure is modeled by utilizing the obtained semantic information of the at least one traffic light, so that at least one traffic light main body model can be obtained; acquiring preset state information of at least one traffic light, and adding the preset state information into at least one traffic light main body model to obtain at least one traffic light target model; adding and storing at least one traffic light target model into a high-precision map to realize the construction of an automatic driving test model; according to the scheme, the traffic light basic structure is modeled by utilizing the semantic information of at least one traffic light to obtain at least one traffic light main body model, and the preset state information is added into the at least one traffic light main body model to obtain at least one traffic light target model, so that a plurality of different traffic light models can be obtained, traffic light standards in actual scenes can be met, manual editing is not needed, and the traffic light basic structure modeling method is convenient, quick and efficient.
In one embodiment of the application, a traffic light infrastructure includes a base portion and an elevated portion connected to one another; the semantic information of the at least one traffic light includes type information of the at least one traffic light; modeling the traffic light infrastructure by using semantic information of at least one traffic light to obtain at least one traffic light main body model, including: adjusting the elevated part by utilizing the type information and preset standard information of at least one traffic light to obtain at least one traffic light initial model; and performing appearance adding processing on the at least one traffic light initial model according to the semantic information of the at least one traffic light to obtain at least one traffic light main body model.
It will be appreciated that the traffic light infrastructure comprises a base portion and an elevated portion connected to each other, wherein the base portion is fixed, non-adjustable; the height and shape of the elevated portion may be adjusted based on semantic information. The semantic information of the at least one traffic light includes at least one traffic light type information, for example, the at least one traffic light type information includes, but is not limited to, a motor vehicle lane traffic light type, a pedestrian traffic light type, or other types of information that can be implemented, without being particularly limited; in addition, the type of the traffic signal lamp of the motor vehicle lane can be correspondingly provided with corresponding lane quantity information, such as bidirectional four lanes and bidirectional eight lanes, and the lane quantity information can correspondingly influence the height and the shape of the elevated part.
Various types of traffic lights are specified in the preset specification information, for example, the preset specification information may be GB-14886, or any other specifications that can be implemented, and is not limited in particular.
And adjusting the elevated part by using the type information of at least one traffic light and preset standard information to obtain at least one initial model of the traffic light. The semantic information may be used to describe the appearance of the traffic light, for example, the color, the material, or other appearance that can be achieved of the traffic light, which is not particularly limited. And according to the semantic information of the at least one traffic light, performing appearance adding processing on the at least one traffic light initial model to obtain at least one traffic light main body model.
For example, the type information may be a vehicle lane traffic light type, the preset standard information is GB-14886, according to the vehicle lane traffic light type, setting and installation standards of the vehicle lane traffic light type are obtained in GB-14886, setting data of a corresponding elevated portion can be obtained, and according to the setting data, the elevated portion is adjusted, so that the adjusted elevated portion meets the setting and installation standards of the vehicle lane traffic light type, and thus a traffic light initial model is obtained. And adding the proper appearance to the traffic light initial model according to the corresponding semantic information to obtain a corresponding traffic light main body model. In this way, a plurality of different traffic light body models can be obtained.
In an embodiment of the present application, the base portion and the elevated portion each include a plurality of constituent units, wherein the shape of the constituent units is a preset polygonal shape; the semantic information of the at least one traffic light further comprises coordinate information; according to the semantic information of at least one traffic light, performing appearance adding processing on at least one traffic light initial model to obtain at least one traffic light main body model, wherein the method comprises the following steps: generating vertex coordinate data of the constituent units according to the coordinate information; acquiring a preset texture picture, and sampling the preset texture picture by using the type information and the vertex coordinate data of at least one traffic light to obtain corresponding sampling data; the sampled data is assigned to the constituent units to obtain at least one traffic light body model.
It will be appreciated that the base portion and the elevated portion each comprise a plurality of constituent units. Fig. 2 is a schematic structural diagram of constituent units according to an embodiment of the present application, and as shown in fig. 2, each constituent unit has a preset polygonal shape, for example, the preset polygonal shape may be a triangle, a quadrilateral, or any other shape that can be implemented, and is not limited specifically. The plurality of constituent units may be the same or different in size, or may be different in size and shape, and may be realized without specific limitation.
The semantic information of the at least one traffic light further comprises coordinate information, from which position coordinates of the base part and the elevated part can be calculated, and also distances between the base part and the lane boundaries can be calculated. It will be appreciated that in some embodiments, the distance between the base portion and the lane boundary may also affect the shape and height of the elevated portion; for example, in adjusting the elevated portion, the elevated portion may be adjusted using the type information of the traffic light and preset specification information, taking into consideration the distance between the base portion and the lane boundary.
According to the coordinate information in the semantic information, vertex coordinate data of each component unit can be calculated. The preset texture picture can be used for adding the appearance of the initial model of the traffic light, the preset texture picture is obtained, the type information and the vertex coordinate data of at least one traffic light are utilized to sample the preset texture picture, corresponding sampling data can be obtained, the sampling data are assigned to corresponding constituent units, and the corresponding at least one traffic light main body model can be obtained.
For example, the overhead part is adjusted by using the type information and the preset standard information of the traffic light to obtain an initial model of the traffic light; the base part and the elevated part in the initial model of the traffic light comprise a plurality of constituent units, and the vertex coordinate data of each constituent unit is obtained by calculation by utilizing the coordinate information in the semantic information; acquiring a preset texture picture, and sampling the preset texture picture by using the type information and the vertex coordinate data of the traffic light to obtain sampling data; according to the vertex coordinate data, giving the sampling data to corresponding component units so as to realize the appearance addition of the initial model of the traffic light and obtain a corresponding main model of the traffic light; in this way, one or more identical or non-identical traffic light body models can be obtained.
In an embodiment of the present application, obtaining a preset texture picture includes: obtaining traffic light appearance data in the road detection data; and cutting the traffic light appearance data to obtain a preset texture picture.
The road detection data acquired by the equipped sensor comprises traffic light appearance data; for example, traffic light image data may be acquired by an image sensor. And cutting the appearance data of the traffic light to obtain a preset texture picture.
It can be appreciated that in other embodiments, the corresponding preset texture picture may also be directly set, which is not limited specifically.
In one embodiment of the application, the traffic light infrastructure further comprises a display portion connected to an end of the elevated portion remote from the base portion; adding preset state information to at least one traffic light body model, comprising: the preset state information is added to the display section.
The traffic light infrastructure further includes a display portion coupled to an end of the elevated portion remote from the base portion, it being understood that the display portion is configured to display the signal light.
The preset state information may include switching sequence data and switching time data between signal lamps, where the switching time data may be set according to an actual scene, for example, when the green light is turned on for 10 seconds, the green light is turned on.
And adding the preset state information to the display part to enable the traffic light main body model to realize the display and switching of the signal lamp, thereby obtaining the traffic light target model.
In an embodiment of the present application, adding preset state information to the display portion further includes: and adding a visual effect to the display part according to the preset specification information.
After the preset state information is added to the display portion, the display portion may be subjected to visual effect processing, i.e., visual effect adding, according to preset specification information, such as GB-14886. For example, a pre-set shape map, brightness, etc. may be added to enable the resulting traffic light target model to more closely conform to the visual effects in the actual scene.
In an embodiment of the present application, obtaining preset status information of at least one traffic light includes: generating traffic light switching sequence data and traffic light switching time data according to semantic information of at least one traffic light; generating preset state information by using the traffic light switching sequence data and the traffic light switching time data; or, acquiring traffic light switching sequence data and traffic light switching time data in the road detection data; and generating preset state information by using the traffic light switching sequence data and the traffic light switching time data.
In an embodiment, traffic light switching sequence data and traffic light switching time data can be generated according to semantic information of traffic lights; for example, according to the semantic information of the corresponding traffic lights, setting the switching sequence among the red lights, the green lights and the yellow lights to generate traffic light switching sequence data, and setting the switching time among the red lights, the green lights and the yellow lights to generate traffic light switching time data. And further, generating corresponding preset state information of the traffic lights by using the obtained traffic light switching sequence data and the traffic light switching time data.
In another embodiment, corresponding traffic light switching sequence data and traffic light switching time data may be obtained from the road detection data collected by the sensor, and then the obtained traffic light switching sequence data and traffic light switching time data are used to generate the preset state information of the corresponding traffic light.
Referring to fig. 3, fig. 3 is a flow chart of a simulation method according to an embodiment of the application, and it should be noted that the method according to the application is not limited to the flow chart shown in fig. 3 if there are substantially the same results. The method can be applied to electronic equipment with functions of calculation and the like, and the electronic equipment can execute the method by receiving data. The electronic device of the present application may be a server, or a system in which a server and a terminal device cooperate with each other. Further, the server may be hardware or software, which is not limited herein. In some possible implementations, the simulation method of the embodiment of the present application may be implemented by a processor calling computer program instructions stored in a memory. As shown in fig. 3, the simulation method includes the steps of:
s21, acquiring driving data of an automatic driving vehicle and an automatic driving test model; the automatic driving test model is obtained according to the automatic driving test model building method.
S22, performing simulation on driving data by using the automatic driving test model to obtain a simulation result.
The automatic driving test model can be utilized to carry out virtual simulation test on driving data of the automatic driving vehicle, and corresponding simulation results are obtained. Further, the driving data may be evaluated using the simulation result.
It will be appreciated by those skilled in the art that in the above-described method of the specific embodiments, the written order of steps is not meant to imply a strict order of execution but rather should be construed according to the function and possibly inherent logic of the steps.
Referring to fig. 4, fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the application. The electronic device 400 comprises a memory 401 and a processor 402 coupled to each other, the processor 402 being adapted to execute program instructions stored in the memory 401 for implementing the steps in the embodiment of the method for constructing an autopilot test model or the steps in the embodiment of the simulation method described above. In one particular implementation scenario, electronic device 400 may include, but is not limited to: the microcomputer and the server are not limited herein.
Specifically, the processor 402 is configured to control itself and the memory 401 to implement the steps in the above-described embodiment of the automatic driving test model constructing method or the steps in the embodiment of the simulation method. The processor 402 may also be referred to as a CPU (Central Processing Unit ), and the processor 402 may be an integrated circuit chip with signal processing capabilities. The processor 402 may also be a general purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), a Field programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. In addition, the processor 402 may be commonly implemented by an integrated circuit chip.
Referring to fig. 5, fig. 5 is a schematic diagram illustrating a structure of a non-volatile computer readable storage medium according to an embodiment of the application. The computer readable storage medium 500 is used for storing program instructions 501, which program instructions 501, when executed by the processor 402, are used for implementing the steps in the above-described embodiment of the automated driving test model construction method or the steps in the embodiment of the simulation method.
The foregoing description of various embodiments is intended to highlight differences between the various embodiments, which may be the same or similar to each other by reference, and is not repeated herein for the sake of brevity.
In the several embodiments provided by the present application, it should be understood that the disclosed methods and related devices may be implemented in other manners. For example, the above-described embodiments of related devices are merely illustrative, e.g., the division of modules or elements is merely a logical functional division, and there may be additional divisions of actual implementation, e.g., elements or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication disconnection between the illustrated or discussed elements may be through some interface, indirect coupling or communication disconnection of a device or element, electrical, mechanical, or other form.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor (processor) to execute all or part of the steps of the methods of the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Claims (10)
1. An automatic driving test model construction method is characterized by comprising the following steps:
acquiring road detection data, a corresponding high-precision map and a traffic light foundation structure for test model construction;
generating semantic information of at least one traffic light in the high-precision map by using the road detection data;
modeling the traffic light infrastructure by utilizing the semantic information of the at least one traffic light to obtain a corresponding at least one traffic light main body model;
acquiring preset state information of the at least one traffic light, and adding the preset state information into the at least one traffic light main body model to obtain at least one traffic light target model;
and adding and storing the at least one traffic light target model into the high-precision map to realize the construction of an automatic driving test model.
2. The method of claim 1, wherein the traffic light infrastructure comprises a base portion and an elevated portion connected to each other; the semantic information of the at least one traffic light includes type information of the at least one traffic light;
the modeling processing is performed on the traffic light infrastructure by utilizing the semantic information of the at least one traffic light to obtain a corresponding at least one traffic light main body model, which comprises the following steps:
adjusting the elevated part by utilizing the type information and preset specification information of the at least one traffic light to obtain the initial model of the at least one traffic light;
and according to the semantic information of the at least one traffic light, performing appearance adding processing on the at least one traffic light initial model to obtain at least one traffic light main body model.
3. The method of claim 2, wherein the base portion and the elevated portion each comprise a plurality of constituent units, wherein the shape of the constituent units is a preset polygonal shape; the semantic information of the at least one traffic light further comprises coordinate information;
the processing of appearance addition is performed on the at least one traffic light initial model according to the semantic information of the at least one traffic light to obtain at least one traffic light main body model, and the processing comprises the following steps:
generating vertex coordinate data of the constituent units according to the coordinate information;
acquiring a preset texture picture, and sampling the preset texture picture by using the type information of the at least one traffic light and the vertex coordinate data to obtain corresponding sampling data;
and giving the sampling data to the component units to obtain the at least one traffic light main body model.
4. A method according to claim 3, wherein said obtaining a preset texture picture comprises:
obtaining traffic light appearance data in the road detection data;
and cutting the traffic light appearance data to obtain the preset texture picture.
5. The method of claim 2, wherein the traffic light infrastructure further comprises a display portion coupled to an end of the elevated portion remote from the base portion;
the adding the preset state information to the at least one traffic light body model includes:
the preset state information is added to the display portion.
6. The method of claim 5, wherein the adding the preset status information to the display portion further comprises:
and adding a visual effect to the display part according to the preset specification information.
7. The method of claim 1, wherein the obtaining the preset status information of the at least one traffic light comprises:
generating traffic light switching sequence data and traffic light switching time data according to the semantic information of the at least one traffic light;
generating the preset state information by using the traffic light switching sequence data and the traffic light switching time data; or alternatively
Acquiring traffic light switching sequence data and traffic light switching time data in the road detection data;
and generating the preset state information by using the traffic light switching sequence data and the traffic light switching time data.
8. A simulation method, comprising:
acquiring driving data of an automatic driving vehicle and an automatic driving test model;
using the automatic driving test model to simulate the driving data so as to obtain a simulation result;
wherein the automatic driving test model is obtained according to the automatic driving test model construction method of any one of claims 1 to 7.
9. An electronic device comprising a memory and a processor coupled to each other, the processor configured to execute program instructions stored in the memory to implement the autopilot test model construction method of any one of claims 1-7 or the simulation method of claim 8.
10. A non-transitory computer readable storage medium storing program instructions which, when executed by a processor, are configured to implement the autopilot test model construction method of any one of claims 1-7 or the simulation method of claim 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310749603.0A CN116822191A (en) | 2023-06-21 | 2023-06-21 | Automatic driving test model construction method, simulation method, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310749603.0A CN116822191A (en) | 2023-06-21 | 2023-06-21 | Automatic driving test model construction method, simulation method, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116822191A true CN116822191A (en) | 2023-09-29 |
Family
ID=88126947
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310749603.0A Pending CN116822191A (en) | 2023-06-21 | 2023-06-21 | Automatic driving test model construction method, simulation method, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116822191A (en) |
-
2023
- 2023-06-21 CN CN202310749603.0A patent/CN116822191A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6548691B2 (en) | Image generation system, program and method, simulation system, program and method | |
| CN111123920A (en) | Method and device for generating automatic driving simulation test scene | |
| US20190065933A1 (en) | Augmenting Real Sensor Recordings With Simulated Sensor Data | |
| CN112199991B (en) | Simulation point cloud filtering method and system applied to vehicle-road cooperation road side perception | |
| CN110807219B (en) | Three-dimensional simulation modeling method, device, terminal and storage medium for road network | |
| CN112382079B (en) | Road side perception analog simulation method and system for vehicle-road cooperation | |
| CN109508579B (en) | Method and device for acquiring virtual point cloud data | |
| CN112270272B (en) | Method and system for extracting road intersections in high-precision map making | |
| WO2018066352A1 (en) | Image generation system, program and method, and simulation system, program and method | |
| CN109931950B (en) | Live-action navigation method, system and terminal equipment | |
| CN116484971A (en) | Automatic driving perception self-learning method and device for vehicle and electronic equipment | |
| CN114859754A (en) | Simulation test method and simulation test system of head-up display system | |
| CN114295139A (en) | Cooperative sensing positioning method and system | |
| CN112860575A (en) | Traffic environment fusion perception in-loop automatic driving algorithm simulation test method | |
| CN111142402A (en) | Simulation scene construction method and device and terminal | |
| CN115424221A (en) | Point cloud and image fusion method, related detection method, device and storage medium | |
| CN115457354A (en) | Fusion method, 3D target detection method, vehicle-mounted device and storage medium | |
| CN112631151A (en) | Simulation test method and device | |
| CN116822191A (en) | Automatic driving test model construction method, simulation method, equipment and medium | |
| CN115830255B (en) | Simulation scene generation method and device, electronic equipment and storage medium | |
| CN115690224A (en) | External parameter calibration method for radar and camera, electronic device and storage medium | |
| CN112906241B (en) | Mining area automatic driving simulation model construction method, mining area automatic driving simulation model construction device, mining area automatic driving simulation model construction medium and electronic equipment | |
| CN111816022A (en) | Simulation method and device for simulation scene, storage medium and electronic equipment | |
| WO2023010540A1 (en) | Method and apparatus for verifying scanning result of laser radar, and device and storage medium | |
| CN115618602A (en) | Lane-level scene simulation method and system |
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 |