CN116050159A

CN116050159A - Simulation scene set generation method, device, equipment and medium

Info

Publication number: CN116050159A
Application number: CN202310087437.2A
Authority: CN
Inventors: 金天
Original assignee: Guangzhou Weride Technology Co Ltd
Current assignee: Guangzhou Weride Technology Co Ltd
Priority date: 2023-02-09
Filing date: 2023-02-09
Publication date: 2023-05-02

Abstract

The invention discloses a simulation scene set generation method, device, equipment and medium. The method comprises the following steps: determining a drive test data set to be processed from the original drive test data set based on at least one screening condition; the drive test data set to be processed comprises at least one group of data to be processed; constructing a multi-dimensional space key data search structure tree based on a drive test data set to be processed; the target drive test simulation set corresponding to the simulation scene generation conditions is determined based on preset simulation scene generation conditions and multidimensional space key data search structure trees, so that the technical problems that the simulation scene set meeting the automatic driving algorithm training requirement cannot be effectively screened out due to low efficiency and low adaptation degree when the simulation scene set is determined are solved, efficient and stable homogenization treatment on the geographic distribution of the simulation scene set is realized, the adaptation degree of the simulation scene set and the automatic driving algorithm training requirement is improved, and the efficiency of generating the simulation scene set is improved.

Description

Simulation scene set generation method, device, equipment and medium

Technical Field

The present invention relates to the field of data processing technologies, and in particular, to a method, an apparatus, a device, and a medium for generating a simulation scene set.

Background

The automatic driving is completed by means of computer and artificial intelligence technology without manual operation. In practical applications, autopilot is implemented by an autopilot algorithm. The autopilot algorithm needs to be trained based on driving scenario data until the autopilot algorithm meets the requirements before being applied to the autopilot vehicle. Thus, training an autopilot algorithm requires driving scenario data.

At present, a large amount of drive test data can be acquired through equipment such as sensors on a vehicle, and the acquired drive test data can be used as driving scene data. In addition, the important scene data in the driving scene data can be marked in a manual mode, and further simulation training is carried out based on the marked important driving scene data.

However, the driving scenario data acquired in the above manner includes a large amount of redundant data, and many of the driving scenario data are relatively simple in scenario, and cannot be used for training an automatic driving algorithm, so that performing a simulation test based on the driving scenario data results in a large amount of resource waste. In addition, the driving scene data can be screened manually, so that not only is the efficiency low, but also subjectivity exists, and the accuracy of a simulation system is low.

Disclosure of Invention

The invention provides a simulation scene set generation method, device, equipment and medium, which realize efficient and stable homogenization treatment on the geographical distribution of a drive test data set, improve the driving scene data coverage efficiency of a simulation system, improve the adaptation degree of the simulation scene set and the automatic driving algorithm training requirement, and improve the efficiency of generating the simulation scene set.

In a first aspect, the present invention provides a method for generating a simulation scene set, where the method includes:

determining a drive test data set to be processed from the original drive test data set based on at least one screening condition; wherein the drive test data set to be processed comprises at least one group of data to be processed;

constructing a multi-dimensional space key data search structure tree based on the drive test data set to be processed;

and determining a target drive test simulation set corresponding to the simulation scene generation conditions based on preset simulation scene generation conditions and the multidimensional space key data search structure tree.

In a second aspect, the present invention provides a simulation scene set generating apparatus, including:

the data set determining module is used for determining a drive test data set to be processed from the original drive test data set based on at least one screening condition; wherein the drive test data set to be processed comprises at least one group of data to be processed;

The search tree construction module is used for constructing a multidimensional space key data search structure tree based on the drive test data set to be processed;

and the simulation set determining module is used for searching a structural tree based on preset simulation scene generating conditions and the multidimensional space key data and determining a target drive test simulation set corresponding to the simulation scene generating conditions.

In a third aspect, the present invention provides a data processing electronic device comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein, the liquid crystal display device comprises a liquid crystal display device,

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the simulation scenario set generation method of any one of the embodiments of the present invention.

In a fourth aspect, the present invention provides a computer readable storage medium storing computer instructions for causing a processor to implement a method for generating a simulation scene set according to any of the embodiments of the present invention when executed.

In a fifth aspect, the present invention provides a computer program product comprising a computer program which, when executed by a processor, implements the simulation scenario set generation method of any one of the embodiments of the present invention.

According to the technical scheme provided by the embodiment of the invention, the to-be-processed drive test data set is determined from the original drive test data set based on at least one screening condition, wherein the to-be-processed drive test data set comprises at least one group of to-be-processed data, and further, a multi-dimensional space key data search structure tree is constructed based on the to-be-processed drive test data set, and then, a target drive test simulation set corresponding to the simulation scene generation condition is determined based on the preset simulation scene generation condition and the multi-dimensional space key data search structure tree. The technical scheme provided by the embodiment of the invention solves the technical problems that the efficiency is low and the adaptation degree is low when the simulation scene set is determined, and the simulation scene set meeting the training requirement of the automatic driving algorithm cannot be effectively screened out, realizes the efficient and stable homogenization treatment on the geographic distribution of the drive test data set, improves the driving scene data coverage efficiency of a simulation system, improves the adaptation degree of the simulation scene set and the training requirement of the automatic driving algorithm, and improves the efficiency of generating the simulation scene set.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a flowchart of a simulation scene set generating method according to a first embodiment of the present invention;

fig. 2 is a flowchart of a simulation scene set generating method according to a second embodiment of the present invention;

fig. 3 is a schematic diagram of a position of coordinate data in a rectangular planar coordinate system according to a second embodiment of the present invention;

FIG. 4 is a schematic diagram of a multi-dimensional spatial key data search structure tree according to a second embodiment of the present invention;

fig. 5 is a schematic structural diagram of a simulation scene set generating device according to a third embodiment of the present invention;

fig. 6 is a schematic structural diagram of an electronic device according to a fourth embodiment of the present invention.

Detailed Description

In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.

It should be noted that, in the description and claims of the present invention and the above figures, the terms "first preset condition", "second preset condition", and the like are used to distinguish similar objects, and are not necessarily used to describe a specific order or precedence. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise 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 1

Before the present technical solution is introduced, an application scenario may be illustrated. The automatic driving is based on an automatic driving algorithm, and before the automatic driving is formally applied to an actual driving scene, a large-scale simulation task is required to improve the performance of an automatic driving algorithm model. Based on the above, the training of the autopilot algorithm requires driving scene data with higher adaptation degree to improve the performance of the autopilot algorithm model. The invention provides a scene set scheme for automatically screening out scene set data matched with the requirements of the automatic driving algorithm from multiple groups of scene set data, which is beneficial to rapidly and efficiently completing the simulation task of the automatic driving algorithm.

Fig. 1 is a flowchart of a simulation scenario set generation method according to a first embodiment of the present invention, where the present embodiment may be applicable to a scenario set that is screened out from a large amount of scenario set data and matches with requirements of an autopilot algorithm. The method may be performed by a simulation scenario set generating apparatus, which may be implemented in hardware and/or software, which may be configured on a computer device, which may be a notebook, a desktop computer, a smart tablet, etc. As shown in fig. 1, the method includes:

s110, determining a drive test data set to be processed from the original drive test data set based on at least one screening condition.

Wherein, the screening conditions are preset conditions. The method is used for screening the drive test data sets matched with screening conditions from a huge number of original drive test data sets. The number of screening conditions may include one or more.

In the present embodiment, the at least one screening condition includes at least one screening factor of a driving state factor, a start point and/or end point factor, a number of obstacles factor, a vehicle travel track factor, and a vehicle travel speed factor. The driving state factor is used for representing whether the vehicle is in an automatic driving state or not; the starting point and/or ending point factors are used for representing whether the starting point and the ending point of a path are marked or not; the obstacle quantity factor is used for representing the quantity of obstacles around the vehicle and the specific positions of the obstacles; the vehicle driving track factor is used for representing a path track corresponding to a certain path travelled by the vehicle; the vehicle driving speed factor is used for representing the speed value of the vehicle during driving and the change condition of the speed.

The original drive test data set is drive test data which is collected in advance and stored in a scene set database. In practical applications, an original drive test data set under various drive test scenarios can be acquired based on the drive test equipment. The drive test equipment can be integrated equipment for collecting various drive test data on the vehicle, or can be special equipment for collecting various drive test data is placed on the vehicle, so that the aim of collecting a large amount of original drive test data is fulfilled. The original drive test data set comprises drive test data corresponding to all roads in a region. The data content in the original drive test data set comprises data tag content corresponding to the screening condition, and the drive test data set corresponding to the screening condition can be found based on the data tag.

The drive test data set to be processed is a data set which is screened from the original drive test data set based on screening conditions and can meet the requirements of simulation tasks. The set of drive test data to be processed includes one or more sets of data to be processed. In the process of collecting the original drive test data set, the drive test equipment can collect data once every fixed time length, so the drive test data to be processed is data with a preset time length, for example, the drive test data with a time length of 10 seconds is data to be processed.

In a specific application process, a database for storing the original drive test data set may be pre-established, then the original drive test data set is collected, and the obtained original drive test data set is stored in the database. In the process of acquiring the original road test data, a data acquisition vehicle can be preconfigured, and runs on each road in a region, and the actual measurement data is acquired based on the road test equipment in the whole process of running.

Because a large amount of redundant data exists in the collected drive test data, if the collected drive test data is directly stored in the database, the waste of database resources is caused, and a large amount of time is required to be consumed in the process of screening the drive test data set to be processed in the original drive test data later, so that invalid data can be screened out first. The invalid data generally originates from the collected data of the message system working properly on the vehicle, which occurs when the driving user has switched the vehicle out of the automatic driving mode. For example, when the driving user wants to stop temporarily, change the route, and does not set a new destination after reaching the destination. The invalid data can be screened in advance, and the operation efficiency of the system can be improved without entering various later processing links. In addition, the purpose of screening out invalid data can be achieved by recording key data points which can be restored for the collected drive test data. In automatic driving, a reasonable trajectory that can reach a destination can be generated using its own path service. Therefore, for the collected drive test data, only the starting point, the end point and the stop site of the path of each piece of data are needed to be stored, the original track of the data can be restored through the path service of the same version to be used for subsequent data processing, and based on the data, the path points on the way can be screened out.

It should be noted that, in the original drive test data, the time or position corresponding to the scene important for the automatic driving algorithm, such as meeting, unprotected left turn, etc., may be recorded, so as to generate the scene set according to the conditions set by the human.

On the basis of the above embodiment, determining a to-be-processed drive test data set from the original drive test data set includes: determining an effective drive test data set from the original drive test data set based on at least one screening condition; and determining a drive test data set to be processed from the effective drive test data set based on at least one preset scene condition.

The valid drive test data can be understood as drive test data which can meet the test requirements of the simulation task. The scene condition is a preset condition. For example, data having a certain scene characteristic in the original drive test data set may be labeled with a corresponding scene label in advance, and a mapping relationship between the scene label and the corresponding data set may be established, based on which a scene set corresponding to the scene label may be determined based on the scene label. The drive test data set to be processed comprises a plurality of drive test data to be processed, and each drive test data to be processed comprises corresponding coordinate data. The coordinate data may represent a spatial geographic location corresponding to the current drive test data to be processed, e.g., may be represented in the form of a coordinate pair.

In this embodiment, when the test user performs simulation training on the autopilot algorithm based on the simulation test set, the test user may determine a condition corresponding to the current simulation task requirement from at least one filtering condition in order to determine a scenario set that meets the simulation task requirement of the test user. After determining the condition corresponding to the current simulation task requirement, determining effective drive test data from the original drive test data based on the determined screening condition, and further determining a scene set corresponding to the scene label from the effective drive test data based on the selected scene label as a drive test data set to be processed.

S120, constructing a multi-dimensional space key data search structure tree based on the drive test data set to be processed.

The search structure tree is a hierarchical structure determined based on the coordinate data of each piece of the drive test data to be processed in the drive test data set to be processed. The search structure tree is used for determining the to-be-processed drive test data with uniform spatial distribution from a plurality of to-be-processed drive test data of the to-be-processed drive test data set.

In this embodiment, the method of constructing the multi-dimensional spatial key data search structure tree may be adopted to construct a k-dimensional tree (kd-Tree). kdtree is a tree data structure for space division, and the data result is that each node can divide the space as uniformly as possible by continuously adjusting the division axis of each point. In the scheme, the kdtree is utilized to enable each passing point to halve the ground plane of the real world as far as possible, so that any number of scenes can be taken out from the to-be-processed drive test data set, and the physical positions of the scenes can be distributed approximately uniformly.

Specifically, after the drive test data set to be processed is determined, the drive test data set to be processed may include a large amount of drive test data to be processed, each drive test data to be processed has coordinate data corresponding to the drive test data set to be processed, and a multidimensional space key data search structure tree can be constructed based on the coordinate data. In the process of constructing the multidimensional space key data search structure tree, the coordinate data corresponding to each piece of drive test data to be processed can be placed in one plane, the plane is further divided into two hyperplanes based on the abscissa corresponding to each piece of drive test data to be processed, further, the two hyperplanes are divided into a plurality of sub-planes according to the ordinate corresponding to the drive test data to be processed, the plane is further divided according to the abscissa corresponding to the drive test data to be processed and the ordinate corresponding to the drive test data to be processed is further divided into planes in the follow-up process, and the planes are alternately arranged until the coordinate data corresponding to all pieces of drive test data to be processed are subjected to plane division, and finally, the root node and the leaf node of the multidimensional space key data search structure tree are determined based on the coordinate data in the planes.

S130, searching a structural tree based on preset simulation scene generation conditions and multidimensional space key data, and determining a target drive test simulation set corresponding to the simulation scene generation conditions.

The simulation scenario generation condition may be understood as the number of simulation scenarios required to complete the simulation task. For example, the simulation scenario generation condition may be "the number of simulation scenario sets required to complete the simulation task is 50 scenario data". The target drive test simulation set is scene set test data which are finally determined and used for carrying out simulation tasks.

In this embodiment, the multi-dimensional spatial key data search structure tree constructed in the above embodiment includes a large amount of scene data, but not every scene data in the search structure tree is used as the target drive test simulation set. The number of simulation scene sets required for completing the simulation task can be preset, and then a sufficient number of scene data are sequentially searched from the root node of the multi-dimensional space key data search structure tree to the leaf nodes to serve as target drive test simulation sets. In the actual application process, the root nodes of the multidimensional space key data search structure tree are sequentially searched for leaf nodes, and the obtained result is a series of coordinate points. The mapping relationship between the coordinate points and the scene data corresponding to the coordinate points may be preset, and after the coordinate points are determined, the scene data corresponding to the coordinate points may be determined as the target drive test simulation set based on the preset mapping relationship.

For example, if 1000 coordinate points are included in the multi-dimensional space key data search structure tree, the simulation scene generating condition may be that "the number of simulation scene sets required for completing the simulation task is 50 scene data", searching is sequentially performed from the root node of the multi-dimensional space key data search structure tree to the leaf node until 50 coordinate data are searched. After determining the 50 coordinate data, 50 scene data corresponding to the 50 coordinate points may be determined as the target drive test simulation set based on a preset mapping relationship.

It should be noted that, in the process of screening the target drive test simulation set, some conditions of human input may be added. Conditions for human input may include, for example: drive test data in the early and late peak period, drive test data belonging to the area A, and the like.

Example two

Fig. 2 is a flowchart of a simulation scene set generating method according to a second embodiment of the present invention, where steps S120 and S130 of the embodiment of the present invention are further refined based on the foregoing embodiments, and the embodiment of the present invention may be combined with each of the alternatives in one or more embodiments. As shown in fig. 2, the method includes:

s210, determining a drive test data set to be processed from the original drive test data set based on at least one screening condition.

S220, coordinate data corresponding to each piece of to-be-processed drive test data in the to-be-processed drive test data set are obtained.

In this embodiment, coordinate data corresponding to each piece of drive test data in the set of drive test data to be processed may be determined, and the coordinate data corresponding to each piece of drive test data to be processed may be stored in the database. In the process of collecting the original drive test data set, the drive test equipment can collect data once every fixed time length, so the drive test data to be processed is data with a preset time length. For example, the drive test device may collect data once every 1 second, and if the drive test data to be processed is drive test data with a duration of 10 seconds, the drive test data to be processed includes 10 data point values. When the coordinate data corresponding to one piece of to-be-processed drive test data in the to-be-processed drive test data set is determined, the abscissa of the coordinate data corresponding to one piece of to-be-processed drive test data can be obtained by averaging the abscissa of the coordinate data of the 10 data point values; and averaging the ordinate of the coordinate data of the 10 data point values to obtain the ordinate of the coordinate data corresponding to certain drive test data to be processed, thereby obtaining the coordinate data corresponding to each drive test data to be processed in the drive test data set to be processed.

For example, if the coordinate data corresponding to the 7 pieces of the drive test data to be processed in the obtained drive test data set are (1, 6), (2, 7), (3, 2), (4, 8), (5, 4), (6,8.5) and (7,1.8), respectively, the positions of the coordinate data in the rectangular planar coordinate system are shown in fig. 3.

S230, determining an intermediate numerical value based on the abscissa of the coordinate data.

On the basis of the above embodiment, the abscissa of the coordinate data of the 7 pieces of drive test data to be processed is 1, 2, 3, 4, 5, 6, 7, respectively, and the intermediate value is 4.

S240, dividing the plane into at least two planes based on the intermediate numerical value, and dividing the at least two planes into a plurality of planes based on the ordinate of the coordinate data in the two planes.

For example, as shown in fig. 3, the coordinate point (4, 8) may be passed on the basis of determining the intermediate value of 4, and a straight line perpendicular to the x-axis is drawn in the plane rectangular coordinate system, so that the plane rectangular coordinate system is divided into two planes, i.e., a left plane and a right plane. In the left plane of fig. 3, 3 coordinate points including (1, 6), (2, 7) and (3, 2); in the right plane of fig. 3, the 3 coordinate points (5, 4), (6,8.5) and (7,1.8) are included. Further, three coordinate points in the left plane of fig. 3 are processed first, the ordinate of the three coordinates is 2, 6 and 7, the intermediate data value of the ordinate is 6, then a (1, 6) coordinate point may be passed, a straight line perpendicular to the y axis may be drawn in the plane rectangular coordinate system, the left plane is divided into two planes of an upper plane and a lower plane, in the upper plane, only a (2, 7) coordinate point may be passed, a straight line perpendicular to the x axis may be drawn in the plane rectangular coordinate system, only a (3, 2) coordinate point may be passed, a straight line perpendicular to the x axis may be drawn in the plane rectangular coordinate system, and the left plane may be divided into 4 planes based on this fig. 3. For three coordinate points in the right plane of fig. 3, the ordinate of the three coordinates is 1.8, 4, 8.5, and the median data value of the ordinate is 4, then a coordinate point of (5, 4) may be passed, a straight line perpendicular to the y-axis may be drawn in the plane rectangular coordinate system, the right plane is divided into two planes of an upper plane and a lower plane, in the upper plane, only a point of (6,8.5) may be passed, so a straight line perpendicular to the x-axis may be drawn in the plane rectangular coordinate system, only a point of (7,1.8) may be passed, so a straight line perpendicular to the x-axis may be passed in the plane rectangular coordinate system, and the right plane may be divided into 4 planes based on this fig. 3.

S250, determining a multi-dimensional space key data search structure tree based on coordinate data in a plurality of planes.

Based on the above examples, a multi-dimensional spatial key data search structure tree determined based on several coordinate data of (1, 6), (2, 7), (3, 2), (4, 8), (5, 4), (6,8.5) and (7,1.8) is shown in fig. 4. As shown in fig. 4, the corresponding coordinates of the first layer of the multi-dimensional spatial key data search structure tree are (4, 8), the corresponding coordinates of the second layer are (1, 6) and (5, 4), and the corresponding coordinates of the third layer are (2, 7), (3, 2), (6,8.5) and (7,1.8).

Based on the above embodiment, the manner of determining the multi-dimensional spatial key data search structure tree may include: based on the coordinate data in the plurality of planes, root nodes and leaf nodes of the multi-dimensional spatial key data search structure tree are determined.

Wherein the root node and the leaf node correspond to respective drive test data to be processed.

For example, as shown in fig. 4, for the multi-dimensional spatial key data search structure tree, the first-level coordinates (4, 8) may serve as a root node of the multi-dimensional spatial key data search structure tree, the second-level coordinates (1, 6) and (5, 4) may serve as leaf nodes of the multi-dimensional spatial key data search structure tree, and the third-level coordinates (2, 7), (3, 2), (6,8.5) and (7,1.8) may serve as leaf nodes of the multi-dimensional spatial key data search structure tree. The root node and the leaf node can be characterized by using coordinate data, and the to-be-processed drive test data corresponding to the root node and the leaf node of the multi-dimensional space key data search structure tree can be determined based on the mapping relation between the coordinate data and the to-be-processed drive test data.

S260, searching at least one node data from the root node of the multi-dimensional space key data searching structure tree based on the number of scenes.

On the basis of the above exemplary embodiments, the simulation scene generation condition includes the number of scenes, that is, the number of scenes may be set in a custom manner, for example, the number of scenes is set to 3, after determining the number of scenes, at least one node data may be searched for from the root node of the multi-dimensional space key data search structure tree in a downstream manner, based on this, two leaf nodes (1, 6) and (5, 4) may be searched for from the root node (4, 8) as shown in fig. 4, and the finally searched at least one node data includes (4, 8), (1, 6) and (5, 4).

S270, generating a target drive test simulation set based on the drive test data to be processed corresponding to the at least one node data.

In this embodiment, based on a mapping relationship between at least one node data coordinate data and the to-be-processed drive test data, to-be-processed drive test data corresponding to the node data of the multi-dimensional space key data search structure tree may be determined, and then the to-be-processed drive test data corresponding to the node data is used as the target drive test simulation set. After the target drive test simulation set is determined, the data contents may be packaged into an overall simulation set, thereby generating the target drive test simulation set. Then, the target drive test simulation set can be directly fed back to a simulation system for test training of an automatic driving algorithm.

According to the technical scheme provided by the embodiment of the invention, the drive test data set to be processed is determined from the original drive test data set based on at least one screening condition, then, coordinate data corresponding to each drive test data set to be processed in the drive test data set to be processed is obtained, an intermediate value is determined based on the abscissa of the coordinate data, the intermediate value is further divided into at least two planes based on the intermediate value, the at least two planes are divided into a plurality of planes based on the ordinate of the coordinate data in the two planes, and a multidimensional space key data search structure tree is further determined based on the coordinate data in the plurality of planes. And then, starting to search at least one node data in a downlink manner from the root node of the multi-dimensional space key data search structure tree based on the scene number, and generating a target drive test simulation set based on the drive test data to be processed corresponding to the at least one node data. The technical scheme provided by the embodiment of the invention solves the technical problems that the efficiency is low and the adaptation degree is low when the simulation scene set is generated, and the training requirement meeting the automatic driving algorithm cannot be effectively screened out, realizes the efficient and stable homogenization treatment on the geographic distribution of the drive test data set, improves the driving scene data coverage efficiency of the simulation system, improves the adaptation degree of the simulation scene set and the automatic driving algorithm training requirement, and improves the efficiency of generating the simulation scene set.

Example III

Fig. 5 is a schematic structural diagram of a simulation scene set generating device according to a third embodiment of the present invention, where the device may execute the simulation scene set generating method according to the embodiment of the present invention. The device comprises: a data set determination module 310, a search tree construction module 320, a simulation set determination module 330.

A data set determining module 310, configured to determine a to-be-processed drive test data set from the original drive test data set based on at least one screening condition; wherein the drive test data set to be processed comprises at least one group of data to be processed;

a search tree construction module 320, configured to construct a multidimensional space key data search structure tree based on the to-be-processed drive test data set;

the simulation set determining module 330 is configured to determine a target drive test simulation set corresponding to the simulation scene generating condition based on a preset simulation scene generating condition and the multi-dimensional space key data search structure tree.

Based on the technical schemes, the original drive test data set under various drive test scenes is acquired based on the drive test equipment.

On the basis of the technical schemes, the at least one screening condition comprises at least one screening factor of driving state factors, starting point and/or ending point factors, barrier quantity factors, vehicle running track factors and vehicle running speed factors.

Based on the above aspects, the data set determining module 310 further includes: an effective data set determining unit and a data set determining unit.

An effective data set determining unit, configured to determine an effective drive test data set from the original drive test data set based on at least one screening condition;

the data set determining unit is used for determining a drive test data set to be processed from the effective drive test data set based on at least one preset scene condition;

the drive test data set to be processed comprises a plurality of drive test data to be processed, and each drive test data to be processed comprises corresponding coordinate data.

Based on the above technical solutions, the search tree construction module 320 further includes: the device comprises a coordinate data acquisition unit, an intermediate data determination unit, a plane division unit and a search tree determination unit.

The coordinate data acquisition unit is used for acquiring coordinate data corresponding to each piece of drive test data to be processed in the drive test data set to be processed;

an intermediate data determination unit configured to determine an intermediate numerical value based on the abscissa of the coordinate data;

the plane dividing unit is used for dividing at least two planes based on the intermediate numerical value and dividing the at least two planes into a plurality of planes based on the ordinate of the coordinate data in the two planes;

And a search tree determination unit for determining a multi-dimensional space key data search structure tree based on the coordinate data in the plurality of planes.

On the basis of the technical schemes, the search tree determining unit is further used for determining root nodes and leaf nodes of the multi-dimensional space key data search structure tree based on coordinate data in a plurality of planes; wherein the root node and the leaf node correspond to respective drive test data to be processed.

Based on the above aspects, the simulation set determining module 330 further includes: and a node data determining unit and a simulation set determining unit.

The node data determining unit is used for searching at least one node data from the root node of the multi-dimensional space key data searching structure tree based on the number of scenes;

and the simulation set determining unit is used for generating a target drive test simulation set based on the drive test data to be processed corresponding to the at least one node data.

The simulation scene set generating device provided by the embodiment of the disclosure can execute the simulation scene set generating method provided by any embodiment of the disclosure, and has the corresponding functional modules and beneficial effects of the executing method.

It should be noted that each unit and module included in the above apparatus are only divided according to the functional logic, but not limited to the above division, so long as the corresponding functions can be implemented; in addition, the specific names of the functional units are also only for convenience of distinguishing from each other, and are not used to limit the protection scope of the embodiments of the present disclosure.

Example IV

Fig. 6 is a schematic structural diagram of an electronic device according to a fourth embodiment of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.

As shown in fig. 6, the electronic device 10 includes at least one processor 11, and a memory, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM13, various programs and data required for the operation of the electronic device 10 may also be stored. The processor 11, the ROM12 and the RAM13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.

Various components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.

The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as the simulation scenario set generation method.

In some embodiments, the simulation scenario set generation method may be implemented as a computer program, which is tangibly embodied on a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM12 and/or the communication unit 19. When the computer program is loaded into RAM13 and executed by processor 11, one or more steps of the simulation scenario set generation method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the simulation scenario set generation method in any other suitable way (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable simulation scenario set generating apparatus, such that the computer programs, when executed by the processor, cause the functions/operations specified in the flowchart and/or block diagram to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.

The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome. It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein. The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.

Claims

1. The simulation scene set generation method is characterized by comprising the following steps of:

2. The method as recited in claim 1, further comprising:

and acquiring an original drive test data set under various drive test scenes based on the drive test equipment.

3. The method of claim 1, wherein the at least one screening condition includes at least one of a driving status factor, a start point and/or end point factor, a number of obstacles factor, a vehicle travel trajectory factor, a vehicle travel speed factor.

4. The method of claim 1, wherein determining a set of drive test data to be processed from the set of raw drive test data based on at least one screening condition comprises:

Determining an effective drive test data set from the original drive test data set based on the at least one screening condition;

determining the drive test data set to be processed from the effective drive test data set based on at least one preset scene condition;

5. The method of claim 1, wherein constructing a multi-dimensional spatial key data search structure tree based on the drive test dataset to be processed comprises:

acquiring coordinate data corresponding to each piece of drive test data to be processed in the drive test data set to be processed;

determining an intermediate value based on the abscissa of the coordinate data;

dividing the intermediate numerical value into at least two planes, and dividing the at least two planes into a plurality of planes based on the ordinate of the coordinate data in the two planes;

the multi-dimensional spatial key data search structure tree is determined based on the coordinate data in the plurality of planes.

6. The method of claim 5, wherein the determining the multi-dimensional spatial key data search structure tree based on the coordinate data within the plurality of planes comprises:

Determining root nodes and leaf nodes of the multi-dimensional space key data search structure tree based on the coordinate data in the planes;

7. The method of claim 1, wherein the simulation scenario generation condition comprises a scenario number, wherein the determining a target drive test simulation set corresponding to the simulation scenario generation condition based on the preset simulation scenario generation condition and the multi-dimensional space key data search structure tree comprises:

searching at least one node data from the root node of the multi-dimensional space key data searching structure tree based on the scene number;

and generating the target drive test simulation set based on the drive test data to be processed corresponding to the at least one node data.

8. A simulation scene set generating apparatus, comprising:

9. An electronic device, characterized in that the electronic device comprises:

one or more processors;

storage means for storing one or more programs,

the simulation scenario set generation method of any one of claims 1-7, when the one or more programs are executed by the one or more processors, causing the one or more processors to implement the method.

10. A storage medium containing computer executable instructions which, when executed by a computer processor, are for performing the simulation scenario set generation method of any one of claims 1-7.