CN115408804A

CN115408804A - Vehicle pose determination method and device

Info

Publication number: CN115408804A
Application number: CN202110579134.3A
Authority: CN
Inventors: 马泽宇
Original assignee: Alibaba Singapore Holdings Pte Ltd
Current assignee: Wuzhou Online E Commerce Beijing Co ltd
Priority date: 2021-05-26
Filing date: 2021-05-26
Publication date: 2022-11-29

Abstract

The present specification provides a vehicle pose determination method and apparatus, wherein the vehicle pose determination method includes: obtaining a road surface patch mark corresponding to the position of a tire of a vehicle at the previous moment; determining the pavement surface patches which have a connection relation with the identified pavement surface patches; determining information to be simulated of a target pavement surface patch according to the pavement surface patches with the connection relation; and determining the pose information of the vehicle at the current moment according to the information to be simulated of the target road surface patch. By the vehicle pose determining method, the information to be simulated of the target pavement surface patch can be rapidly determined, so that the pose of the vehicle can be determined in real time, and the coverage in a simulation test scene is improved.

Description

Vehicle pose determination method and device

Technical Field

The specification relates to the technical field of computers, in particular to a vehicle pose determining method. The present specification also relates to a vehicle pose determination apparatus, a computing device, and a computer-readable storage medium.

Background

With the development of internet technology, a vehicle dynamics theory is widely applied to vehicle motion simulation of automatic driving simulation, and key information such as speed, acceleration, vehicle body pitching and the like of a simulated vehicle can be accurately provided, so that an automatic driving algorithm can smoothly run in a virtual environment. One key point of vehicle motion simulation is how to quickly solve the tire grounding point, but because the area of a scene for operating an automatic driving vehicle is large, the number of triangles obtained by triangularizing a set scene is large, and the influence of integral precision and convergence is caused, the vehicle dynamics calculation frequency generally exceeds 1000hz, and it is difficult to determine the triangle to which the tire grounding point belongs in a short time, so an effective scheme is urgently needed to solve the problems.

Disclosure of Invention

In view of this, the embodiments of the present specification provide a vehicle pose determination method. The present specification also relates to a vehicle pose determination apparatus, a computing device, and a computer-readable storage medium to address technical deficiencies in the prior art.

According to a first aspect of embodiments herein, there is provided a vehicle pose determination method including:

obtaining a road surface patch mark corresponding to the position of a tire of a vehicle at the previous moment;

determining the pavement patches which have connection relations with the marked pavement patches;

determining information to be simulated of a target pavement surface patch according to the pavement surface patches with the connection relation;

and determining the pose information of the vehicle at the current moment according to the information to be simulated of the target road surface patch.

Optionally, different pavement patches have different information topologies, including but not limited to: the mark, the coordinate and the boundary point mark of the pavement surface patch are connected with each other;

then, the determining the pavement surface patch having a connection relationship with the identified pavement surface patch includes:

and determining the road surface patches with the connection relation with the road surface patches corresponding to the positions at the previous moment according to the connection relation among the information topologies.

Optionally, the determining, according to the road surface patches with the connection relationship, information to be simulated of a target road surface patch includes:

obtaining boundary point identifications corresponding to the road surface patches with the connection relation, and determining normal vectors corresponding to the target road surface patches according to the boundary point identifications;

obtaining the coordinates of the intersection point of the tire coordinate system axis vector of the vehicle and the road surface patch with the connection relation;

and taking the normal vector and the intersection point coordinate as information to be simulated.

Optionally, the obtaining of the road surface patch identifier corresponding to the position of the tire of the vehicle at the previous time includes:

obtaining the coordinates of the central point of the tire of the vehicle at the previous moment;

and determining the road surface patch projected by the central point coordinate, and determining the road surface patch identification of the road surface patch projected by the central point coordinate.

Optionally, the pavement surface patch is a triangle, and the boundary point identifier is a triangle vertex identifier.

Optionally, the determining information to be simulated of the target pavement surface patch according to the pavement surface patch with the connection relationship includes:

determining a target pavement patch to which a contact point of a tire of the vehicle and a pavement belongs from the pavement patches with the connection relation according to a preset search strategy;

and determining information to be simulated of the target pavement surface patch.

Optionally, the determining, according to the information to be simulated of the target road surface patch, pose information of the vehicle at the current time includes:

and inputting the information to be simulated to a preset pose recognition module for processing to obtain the pose information of the vehicle at the current moment.

According to a second aspect of embodiments herein, there is provided a vehicle pose determination apparatus including:

the identification obtaining module is configured to obtain a road surface patch identification corresponding to the position of the tire of the vehicle at the last moment;

a patch determining module configured to determine a pavement patch having a connection relationship with the identified pavement patch;

the determining information module is configured to determine information to be simulated of a target pavement surface patch according to the pavement surface patches with the connection relation;

and the pose determining module is configured to determine pose information of the vehicle at the current moment according to the information to be simulated of the target road surface patch.

According to a third aspect of embodiments herein, there is provided a computing device comprising:

a memory and a processor;

the memory is to store computer-executable instructions, and the processor is to execute the computer-executable instructions to:

According to a fourth aspect of embodiments herein, there is provided a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the vehicle pose determination method.

According to the vehicle pose determining method provided by the specification, after the road surface patch identification corresponding to the position of the tire of the vehicle at the previous moment is obtained, the road surface patch with the connection relation with the road surface patch of the identification can be determined, the information to be simulated of the target road surface patch is determined on the basis of the road surface patch with the connection relation, and finally the pose information of the vehicle at the current moment can be determined on the basis of the information to be simulated, so that the target road surface patch can be rapidly determined on a tiled road surface, the pose of the vehicle can be accurately analyzed, the coverage of a simulation test scene is improved, the pose determining speed cannot be influenced due to scene change, and the detection capability of the vehicle under the current scene is effectively improved.

Drawings

Fig. 1 is a schematic structural diagram of a vehicle pose determination method provided in an embodiment of the present specification;

FIG. 2 is a flow chart of a vehicle pose determination method provided by an embodiment of the present disclosure;

fig. 3 is a schematic diagram of a surface patch to which a contact point belongs in a vehicle pose determination method provided in an embodiment of the present specification;

fig. 4 is a schematic view of a tire coordinate system in a vehicle pose determination method provided in an embodiment of the present specification;

FIG. 5 is a flowchart illustrating a vehicle pose determination method applied to a simulation scenario according to an embodiment of the present disclosure;

fig. 6 is a schematic structural diagram of a vehicle pose determination apparatus provided in an embodiment of the present specification;

fig. 7 is a block diagram of a computing device according to an embodiment of the present disclosure.

Detailed Description

In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present specification. This description may be implemented in many ways other than those specifically set forth herein, and those skilled in the art will appreciate that the present description is susceptible to similar generalizations without departing from the scope of the description, and thus is not limited to the specific implementations disclosed below.

The terminology used in the description of the one or more embodiments is for the purpose of describing the particular embodiments only and is not intended to be limiting of the description of the one or more embodiments. As used in one or more embodiments of the present specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used in one or more embodiments of the present specification refers to and encompasses any and all possible combinations of one or more of the associated listed items.

It should be understood that although the terms first, second, etc. may be used herein in one or more embodiments to describe various information, these information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, a first can be termed a second and, similarly, a second can be termed a first without departing from the scope of one or more embodiments of the present description. The word "if," as used herein, may be interpreted as "at \8230; \8230when" or "when 8230; \823030when" or "in response to a determination," depending on the context.

In the present specification, there is provided a vehicle pose determination method, and the present specification relates to a vehicle pose determination apparatus, a computing device, and a computer-readable storage medium, which are described in detail one by one in the following embodiments.

In practical application, with the improvement of the computing performance of a computer, the computer is required to complete real-time computation in many scenes, such as the automatic driving scene of a motor vehicle, and the driving information of the motor vehicle is required to be computed in real time; or the carrying robot carries goods scene, and the motion trail of the carrying robot needs to be calculated in real time; then or the shopping guide robot moves the scene, need to calculate the movement track of the robot in real time; real-time computation is involved. The core of the method is to calculate the contact point of the moving object relative to the road surface, so as to analyze the road condition information of the moving object in the current moving scene, and reflect the pose of the moving object, so that the moving object can be conveniently adjusted to adapt to the road condition in the current scene.

In the prior art, when determining the contact point of a moving object and a road surface, a ray intersection method provided by an open source physical engine Physx and a method for returning road surface geometric information by using a high-precision map are generally adopted. In the ray intersection method provided by the physics engine PhysX, the essence is to perform intersection on the tire of a moving object and a road surface triangular patch based on the high-performance computing capability of the GPU, and find out the triangle where the tire grounding point is located. The method for returning the geometric information of the road surface by the high-precision map adopts a means that the road condition information of any point can be returned by a high-precision map format (such as open-drive, lmap). The method is used for attitude simulation of moving object dynamics, but the method strongly depends on map collected data, can not customize a special road surface, and a high-precision map cannot accurately describe micro small terrains and accurately reflect real-time road condition information, so that an effective scheme is urgently needed to solve the problems.

In view of this, the present specification provides a vehicle pose determination method, and as shown in fig. 1, the tire road surface contact point initial value calculation module, the road surface patch structure information topology module, the tire road surface contact point iterative search module, the line and plane intersection point calculation module, and the vehicle dynamics model are mutually matched to realize rapid vehicle pose determination. The method comprises the steps of obtaining a road surface patch identification corresponding to the position of a tire of a vehicle at the previous moment, determining a road surface patch in a connection relation with the road surface patch of the identification, determining to-be-simulated information of a target road surface patch based on the road surface patch in the connection relation, and determining pose information of the vehicle at the current moment based on the to-be-simulated information.

Fig. 2 shows a flowchart of a vehicle pose determination method provided in an embodiment of the present specification, which specifically includes the following steps:

step S202, a road surface patch identifier corresponding to a position of a tire of the vehicle at the previous time is obtained.

The vehicle pose determining method provided by the embodiment can be applied to solving the vehicle pose scene under the complex road surface, or solving the carrying truck pose scene under the complex carrying scene, or solving the sightseeing trolley pose scene under the complex market environment, and the like. That is, the vehicle with the determined pose is a vehicle with a movement requirement, including but not limited to a vehicle such as an automobile or a trolley, and the embodiment is not limited in any way herein.

Correspondingly, the road surface corresponding to the position at the previous moment specifically refers to the road surface contacted by the tire of the vehicle and the road surface in the previous calculation cycle, and correspondingly, the road surface patch identification is the unique identification of the corresponding patch after the road surface is subjected to the patch processing.

Based on this, because the road surface environment contacted by the mounted tire of the vehicle may be complex in the automatic moving scene, if the posture of the vehicle in the current road surface environment needs to be fed back in time, the information to be simulated of the road surface needs to be calculated in real time first to support the solution of the posture of the vehicle in the current scene from the information to be simulated of the road surface, so that the fidelity of the vehicle simulation model is increased, the detection capability in the extreme scene is improved, and the influence of the vehicle on the road surface in the automatic moving scene is controlled.

In the process, because real-time calculation is required, if the calculation delay is high or the performance requirement on a computer is high, the pose of the vehicle cannot be determined in time, and therefore the authenticity of the vehicle in the current scene cannot be reflected. In order to improve the efficiency and accuracy of determining the pose of the vehicle in the process, a patch structure information pre-established mode can be used for assisting in determining a target pavement patch, so that to-be-simulated information corresponding to the target pavement patch in the current calculation period can be rapidly determined, the pose of the vehicle can be determined according to the to-be-simulated information, the pose of the vehicle can be accurately analyzed, the coverage of simulation test can be improved, the determination rate of the pose cannot be influenced due to scene change, and the detection capability of the vehicle in the current scene is effectively improved.

Further, the patches specifically refer to patches corresponding to a road surface after being subjected to a tiling process, and in the method for determining a vehicle pose provided by this embodiment, the patches specifically refer to patches obtained after the road surface is subjected to a triangular tiling process, so that each patch is triangular. Because the road surface after the triangle facet ization can correspond a large amount of triangle facets, and different triangle facets map different road conditions, consequently need set up the sign to each triangle facet, promptly the road surface facet sign is the only sign that each triangle facet has promptly. In practical application, when the road surface is subjected to the tiling processing, quadrilateral tiling processing or polygonal tiling processing can be performed according to requirements, and only the requirement that the information to be simulated corresponding to the tire and the road surface at the next moment can be determined quickly in the following process is met, and the embodiment is not limited herein.

Correspondingly, because the vehicle is in a moving state, the contact point of the tire and the road surface continuously changes, and in the process of changing, the triangular patch to which the contact point belongs also changes along with the movement of the vehicle, so that the patch to which the contact point of the tire and the road surface belongs in the current calculation period can be quickly calculated, the road surface patch identifier corresponding to the tire position in the previous moment can be obtained, the goal road surface patch to which the tire needs to be contacted in the next moment is finished from the road surface patch identifier in the previous moment, and the vehicle pose is determined by determining the to-be-simulated information of the goal road surface patch.

Furthermore, in the process of determining the patch identifier corresponding to the contact point between the tire and the road surface at the previous time, in view of the precision problem, a projection mapping manner may be adopted, and in this embodiment, a specific implementation manner is as follows:

obtaining the coordinates of the central point of the tire of the vehicle at the last moment;

Specifically, the central point coordinate specifically refers to a coordinate corresponding to the tire at the previous moment, and the pavement patch projected by the central point coordinate is a patch to which the contact point belongs when the tire is in contact with the pavement at the previous moment; correspondingly, the pavement surface patch identification is the unique identification of the surface patch.

In practical application, because a tire has a certain volume and can change along with the movement of a vehicle, if the positioning of a patch to which a contact point belongs is carried out in real time during the movement, extra computing resources may be generated, and the efficiency of determining the pose of the vehicle is reduced, so that the road surface patch identification is determined in a positioning center point coordinate mapping mode; that is, when a patch at the next moment needs to be calculated, the center point coordinate of the tire of the vehicle at the previous moment can be obtained, then the center point coordinate is projected to the pavement patch corresponding to the pavement, the patch where the projection point is located is taken as the patch where the tire and the pavement contact point at the previous moment belong, and the identification of the patch is determined.

In conclusion, the road surface patch identification is determined in a tire center point projection mode, so that the calculation efficiency can be improved, calculation resources can be saved, and the subsequent quick determination of the vehicle pose can be achieved.

And step S204, determining the pavement patches with the connection relation with the marked pavement patches.

Specifically, on the basis of the above-mentioned road surface patch identifier to which the contact point between the tire and the road surface belongs, further, in consideration of a high requirement for the calculation efficiency in a current scene, in order to be able to quickly determine the target road surface patch in the current calculation cycle in a short time, the determination may be completed by combining the road surface patches having a connection relationship with the road surface patches corresponding to the identifier, so as to save the time for determining the target road surface patch in the current calculation cycle, thereby improving the subsequent processing efficiency, where the road surface patches having the connection relationship specifically refer to the road surface patches having an edge connection relationship with the road surface patches corresponding to the identifier and a vertex connection relationship with the road surface patches corresponding to the identifier, that is, the road surface patches of this part are connected with the road surface patches corresponding to the position at the previous time.

In practical applications, in order to quickly determine the pavement surface patches with the connection relationship, different information topologies may be set in advance for different pavement surface patches, where the information topologies include but are not limited to: the mark, the coordinate and the boundary point mark of the pavement surface patch are connected with each other; that is to say, the identification, the vertex coordinates, the boundary point identification and other patches with connection relations of each pavement patch can be determined through the information topology of each pavement patch, so that the subsequent determination of the pavement patches with connection relations can be completed from the information topology.

It should be noted that, because the vehicle pose determining method provided by this embodiment is applied in a simulation scene, the information topology corresponds to and is known as the road surface, that is, the information topology stores a corresponding road surface structure information topology file, so that the relevant information can be determined by reading the corresponding topology file according to the simulation scene.

Further, the coordinates in the information topology are used for recording three-dimensional coordinate information of points in the road surface; for example, a roadpointinfo. Conf table exists in the coordinates in the information topology, and the table structure is shown in the following table 1, and is used for storing the three-dimensional coordinates of points in the road surface:

point ID	X coordinate	Y coordinate	Z coordinate
				ID_l	X l	Y l	Z l

TABLE 1

The boundary point identifier in the information topology is used to record coordinate information and identification information of a vertex of each patch in the road surface, and it should be noted that the boundary point identifier corresponds to a coordinate corresponding to a point of the road surface. For example, a roadtriangle info. Conf table exists in the boundary point identifier in the information topology, and the table structure is shown in the following table 2, and is used for storing the vertex ID of each triangle patch generated by the road surface point, where the ID corresponds to the roadpointinfo. Conf table:

triangle ID	Vertex	1 Point ID	Vertex 2 Point ID	Vertex 3 Point ID
					ID_l	ID_l_1	ID_l_2	ID_l_3

TABLE 2

The connection relation among the information topologies is used for recording the information of the adjacent patches of each patch in the road surface; it should be noted that the mutual connection relationship is associated with the road point coordinate information. For example, a roadtoppolytriangleinfo. Conf table exists in the connection relationship among the information topologies, and the table structure is shown in the following table 3, and is used for storing the corresponding connection relationship among the road surface triangle patches, since the connection relationship between a triangle and a triangle is divided into edge adjacency and vertex vector, n adjacent triangles are recorded, and the triangle ID is consistent with the roadtriglycengleinfo. Conf table:

triangle ID	Edge-adjacent triangle ID set	Vertex-adjacent triangle ID set
			ID＝l	E _ID＝l ＝{ID ₁ ，ID ₂ ，ID ₃ }	P _ID＝l ＝{ID ₄ ，ID ₅ ，ID ₃ ，…，ID _n } _l

TABLE 3

Furthermore, in the process of determining the road surface patches with connection relationships, because there are many patches corresponding to the road surface, in order to save time, the road surface patches with connection relationships may be determined by combining information topologies of the road surface patches, and in this embodiment, a specific implementation manner is as follows:

Specifically, since the information topology records other patches to which each pavement patch is connected in the connection relationship with each other, in order to quickly determine the target pavement patch in the subsequent process, the information topology may determine the pavement patch having the connection relationship with the pavement patch corresponding to the previous position in the connection relationship with each other, so as to facilitate the subsequent process.

In practical application, because other patches having connection relations with the pavement patches corresponding to the identifiers may have vertex connection relations and edge connection relations, when the pavement patches having connection relations are determined, all the pavement patches having vertex connection relations and edge connection relations with the pavement patches corresponding to the identifiers can be selected as the pavement patches having connection relations, so that processing operations of traversing all the patches corresponding to the pavement are reduced, the target pavement patches are screened from the part of the pavement patches, the calculation efficiency is improved to a great extent, and the vehicle pose can be rapidly determined.

And step S206, determining the information to be simulated of the target pavement surface patch according to the pavement surface patches with the connection relation.

Specifically, on the basis of determining the road surface patches with the connection relationship, in order to quickly determine the vehicle pose, the target road surface patches may be determined from the road surface patches with the connection relationship, and then the subsequent pose calculation may be completed by determining the to-be-simulated information of the target road surface patches. The target pavement surface patch specifically refers to a surface patch to which a tire and a pavement contact point belong at the next moment, and correspondingly, the information to be simulated specifically refers to information representing road conditions of the pavement, so that the pose of the vehicle at the next moment can be calculated.

Further, in the process of determining the information to be simulated of the target road surface patch, only the accuracy of the information to be simulated is ensured, so that the pose of the vehicle can be accurately solved, and therefore, in order to accurately determine the target road surface patch from the road surface patches with the connection relationship, a search strategy can be adopted to complete the determination of the target road surface patch, and in this embodiment, the specific implementation manner is as follows:

and determining the information to be simulated of the target pavement surface patch.

Specifically, because the motion of the vehicle is continuous, the patches to which the contact points of the tire and the road surface belong should also be continuous, that is, the patch to which the contact point belongs at the previous moment and the patch to which the contact point belongs at the next moment are adjacent, so that the information topology of each patch can be queried through the identified road surface patch, and the road surface patch with the connection relationship can be determined therefrom; and then determining a target pavement surface patch to which a contact point of the tire of the vehicle and the pavement belongs from the pavement surface patches with the connection relation according to a search strategy, and determining information to be simulated of the surface patch to be used for subsequently calculating the pose of the vehicle.

That is, the pavement surface patches with connection relation are composed of the surface patches adjacent to the marked pavement surface patches; correspondingly, the search strategy specifically refers to a strategy for determining the target pavement surface patch, which is a surface patch to which a contact point between the pavement and the tire at the next moment belongs.

Further, in the process of determining the target pavement surface patch, in order to improve the determination efficiency, a central point of the tire at the previous moment and a central point of the tire at the next moment are obtained; then calculating the Euclidean distance between the central point of one moment and the central point of the next moment; and finally, searching the road surface patches with the connection relation according to the preset distance condition and the Euclidean distance, and determining the target road surface patches to which the contact points of the tires and the road surface belong at the next moment according to the search result.

In conclusion, by searching the target pavement patches in the pavement patches with the connection relation, the time for searching the target pavement patches in the whole situation can be saved, the searching accuracy is effectively guaranteed, and the pose determining efficiency is improved.

In practical application, when the target pavement surface patch is determined, the target pavement surface patch of the surface patch to which the contact point of the road surface and the tire belongs at the next moment is quickly searched according to the mark of the pavement surface patch to which the known contact point of the road surface and the tire belongs at the last moment and the corresponding connection relation between the surface patches stored in the information topology corresponding to the pavement surface patch. That is to say, the above-mentioned mode of determining the target pavement patch is to adopt the edge iterative search, and each calculation cycle only needs to search in the patches connected with the pavement patches corresponding to the identifier at the previous moment, so that the target pavement patch can be rapidly determined without performing global search, and meanwhile, the method is not influenced by the number of patches corresponding to the pavement under the current scene, and therefore, the calculation efficiency can be effectively improved.

In specific implementation, because the contact points of the road surface and the tire may be located at different positions of different patches, in order to accurately determine the patch to which the contact point belongs in each calculation cycle, the determination may be performed in advance, that is, the distance from the center point of the tire to the triangle corresponding to the road surface is defined as the euclidean distance from the center point to the center of gravity of the triangle, that is, dis = ([ delta ]) _id ，pt)＝||gravity-pt|| ₂ Defining a triangle delta if the projection point of the point pt on the horizontal plane x-o-y _id Inside the projection of the horizontal plane x-o-y, the point pt is then defined at the triangle Δ _id Internal, i.e. in (. DELTA.) _id Pt) = true, otherwise outside the triangle, i.e. in (. DELTA.) _id ，pt)＝false。

In practical application, in order to quickly determine a target road surface patch, the processing procedure may be packaged in a tire road surface contact point iterative search algorithm module, and during searching, a search flag ok _ search = false may be initialized, and a sequence with a length of N may be initialized for storing a triangle Δ corresponding to a searched road surface _id And a target center point W of the tire at the next moment _c ^tk Is marked as Vec<dis(△ _id ，W _c ^tk )>Where dis denotes Δ _id Center of gravity and target center point W _c ^tk Euclidean distance of (d), denoted as dis (Δ) _id ，W _c ^tk )，Vec<dis(△ _id ，W _c ^tk )>The Euclidean distance between the searched patch and the target central point is stored, when the target central point is in an adjacent triangle of id _ base, the search is successful, the flag is ok _ search = true, otherwise, the flag is from Vec<dis(△ _id ，W _c ^tk )>Find the smallest triangle id ^tk-1 Starting a new round of edge searching as id _ base, and determining the target pavement patch by traversing the set searching.

To illustrate, the target vehicle is runningThe driving place is G, and when the body posture of the simulation vehicle is required to be simulated under the current scene, the patch identification of the patch to which the tire of the target vehicle belongs and the road surface contact point in the t-1 calculation period is determined to be id _ l ^tk ^-1 At this time, the patch identification id _ l may be determined in combination with the information stored in the above tables (1) to (3) ^tk-1 The adjacent patch has { id _2 ^tk-1 ,id_3 ^tk-1 ,id_4 ^tk-1 ,…id_n ^tk-1 And since the maximum vehicle speed of the vehicle in the automatic driving mode is 30m/s, that is, the vehicle running distance is 0.03m at 1ms, the center point W of the vehicle in the t-1 calculation cycle is determined _c ^tk-1 And the center point W in the calculation cycle of t _c ^tk The distance does not exceed 0.03m, i.e. the centre point W _c ^tk-1 And W _c ^tk S, so that by searching the triangle 53 times, the patch identification corresponding to the patch to which the contact point of the tire and the road surface belongs in the t calculation period can be determined to be id _ s ^tk-1 (s is n or less and s is a positive integer), see t-1 shown in FIG. 3 for calculating the period center point W _c ^tk-1 Calculating the central point W of the period of the patch and t _c ^tk The schematic diagram of the corresponding patch is used for facilitating the subsequent calculation of the patch identifier id _ s corresponding to the patch to which the contact point of the tire and the road surface belongs in the period according to t ^tk-1 And solving the posture of the vehicle body, and simulating the vehicle state under the real road condition.

In this process, the center point W of the calculation cycle at t-1 is determined _c ^tk-1 The associated patch is located in the first area of fig. 3, i.e., the initialization stage seed triangle id _ base = id _ l ^tk-1 At this time, the current patch is identified as id _ l ^tk-1 Adjacent patch { id _2 } ^tk-1 ,id_3 ^tk-1 ,id_4 ^tk-1 ,…id_n ^tk-1 Searching for the center point W in the computation period of t in the (f) _c ^tk The belonged patch is to be noted because the associated patch is identified as id _ l ^tk-1 Adjacent patches include edge neighbors and vertex neighbors, so its neighboring patch { id _2 } ^tk-1 ,id_3 ^tk-1 ,id_4 ^tk-1 ,…id_n ^tk-1 Will be bounded by side-adjacent triangles and vertex phaseAdjacent triangles. Further, in the case of batch =1, it is determined through calculation that the center point of the tire is located in the (1) area in fig. 3, at this time, id of the triangle patch having the smallest distance from the center point is used as id _ base, and batch +1, at this time, ok _ search ≠ true is determined, then, search processing of batch =2 is performed, and when the triangle patch having the smallest distance from the center point in the second search according to the search result is located in the (2) area in fig. 3, at this time, id of the triangle is used as id _ base, and batch +1, and ok _ search ≠ true is determined, then, search processing of batch =3 \8230 \\\ 8230:, until ok _ search = true indicates that the center point W is determined in the current calculation cycle _c ^tk The patch is determined to be located in the (8) area in fig. 3 according to the search result, and the identification of the patch is id _ s ^tk-1 To facilitate subsequent processing.

In conclusion, the target pavement patches are determined from the pavement patches with the connection relation, so that the calculation efficiency is improved, the subsequent vehicle pose determination efficiency is promoted, the pose determination accuracy and efficiency are effectively guaranteed, and the pose solving efficiency in a simulation scene is improved.

Furthermore, after the determination of the target road surface patch is completed, the information to be simulated at the next moment can be determined from the target road surface patch, so as to facilitate the subsequent solution of the pose of the vehicle, in this embodiment, the process of determining the information to be simulated is as follows:

Specifically, the boundary point identifier specifically refers to a boundary point identifier corresponding to each of the road surface patches with a connection relationship, that is, an identifier corresponding to a vertex of each of the road surface patches; correspondingly, the normal vector is calculated based on the boundary point identifier of the target road surface patch after the target road surface patch is determined.

Based on this, when the information to be simulated is determined, firstly a target road surface patch is determined, then the boundary point identifier of the target road surface patch is selected to calculate the normal vector, meanwhile, the tire coordinate system axis vector of the vehicle and the intersection point existing between the tire coordinate system axis vector and the target road surface patch are obtained, the coordinate of the intersection point is determined, and finally, the normal vector and the intersection point coordinate are used as the information to be simulated for carrying out the subsequent ball solution of the vehicle position.

In specific implementation, the calculation of the normal vector is to calculate the normal vector of the patch according to the (boundary point identification) vertex coordinates in the information topology of the target pavement patch; the actual coordinates of the intersection points are the coordinates of the points where the target road surface patch intersects with the axis vector of the tire coordinate system of the vehicle.

In practical application, in order to improve the efficiency of determining information to be simulated of a target pavement patch, the determination implementation mode can be packaged in a line-plane intersection point solving module to provide a coordinate system axis vector of a tire coordinate system in real time through a vehicle dynamic model suspension assembly, meanwhile, three vertex coordinates corresponding to the target pavement patch can be searched in the information topology of the target pavement patch based on the target pavement patch provided by a tire pavement contact point iterative search module, so that a normal vector of the target pavement patch is obtained, and meanwhile, the contact point coordinates can be obtained according to the coordinate system axis vector and the coordinates of the intersection point of the target pavement patch plane to determine the information to be simulated of the target pavement patch

Furthermore, after the determination of the information to be simulated of the target road surface patch is completed, the information to be simulated may be input to a preset pose recognition model for processing, so as to obtain the pose of the vehicle, which is specifically implemented as follows:

Following the above example, see the schematic diagram shown in FIG. 4, pt1, pt2 and pt3 constitute a patch ID _ s ^tk-1 When the pose of a vehicle under the current scene needs to be determined, the corresponding target triangular patch can determine patch identification id _ s according to the pre-stored structure information of the road surface triangular patch ^tk-1 The three vertexes of the corresponding triangular surface patch are (pt 1, pt2 and pt 3), wherein the coordinate of the vertex pt1 is (x 1, y1 and z 1); the vertex pt2 has coordinates of (x 2, y2, z 2); the vertex pt3 has coordinates of (x 3, y3, z 3); at this time, the normal vector coordinate g is represented By the plane equation Ax + By + Cz + D =0 _z ＝[A,B,C]The normal vector can be calculated, wherein,

d = - (Ax 1+ By1+ Cz 1), and A ₁ ，B ₁ ，C ₁ And the coordinate relationship of the vertex of the triangular patch is as follows: a. The ₁ ＝(y2-y1)(z3-z1)-(z2-z1)(y3-y1)；B ₁ ＝(x3-x1)(z2-z1)-(x2-x1)(z3-z1)；C ₁ ＝(x2-x1)(y3-y1)-(x3-x1)(y2-y1)。

Further, the normal vector g is determined _z Meanwhile, the coordinates of the grounding point Wg are required to be obtained, and the linear equation of the vector of the Wz axis of the tire coordinate system is known as follows:

and

the tire grounding point Wg coordinate solving method is w _g ＝-A ^-1 D, wherein

According to the normal vector g _z And the coordinates of a tire grounding point Wg can determine the geometric information of the road surface, and then the geometric information of the road surface is directly input into a vehicle model dynamic integrator to be used for solving the position and posture of the vehicle body under a complex road surface, so that the running of the vehicle in a G scene can be determinedDuring operation, the postures of the vehicle body under different road conditions (such as a ramp, a deceleration strip and a pothole) are increased, so that the fidelity of the measurement simulation model is increased, and the detection capability of the simulation engine on the automatic driving algorithm under an extreme scene is improved.

In addition, in order to simulate the motion state of the vehicle more truly, the vehicle may be adjusted after the pose is determined, and in this embodiment, a specific implementation manner is as follows:

adjusting the vehicle based on the pose information, and determining a motion track and motion information corresponding to the vehicle according to an adjustment result;

and updating the motion state of the vehicle according to the motion trail and the motion information.

According to the above example, when the situation that the vehicle body deviates due to the fact that the vehicle passes through the deceleration strip in the t calculation period is simulated, in order to keep the vehicle running normally, the angle of the tire can be adjusted, the new motion track and the new speed are determined, then the vehicle is controlled to move according to the new motion track and the new speed, and the vehicle is guaranteed to continue to drive automatically.

According to the vehicle pose determining method provided by the specification, after the road surface patch identification corresponding to the position of the tire of the vehicle at the previous moment is obtained, the road surface patch with the connection relation with the road surface patch of the identification can be determined, the information to be simulated of the target road surface patch is determined on the basis of the road surface patch with the connection relation, and finally the pose information of the vehicle at the current moment can be determined on the basis of the information to be simulated, so that the target road surface patch can be rapidly determined on a tiled road surface, the pose of the vehicle can be accurately analyzed, the coverage of a simulation test scene is improved, the pose determining speed cannot be influenced by scene change, and the detection capability of the vehicle under the current scene is effectively improved.

The following further describes the vehicle pose determination method, by taking an application of the vehicle pose determination method provided in this specification in a simulation scene as an example, with reference to fig. 5. Fig. 5 shows a processing flow chart of a vehicle pose determination method applied to a simulation scene according to an embodiment of the present specification, and specifically includes the following steps:

step S502, obtaining an initial triangular patch identification of a triangular patch to which a contact point of a tire of a vehicle and a road surface at the previous moment belongs.

And step S504, determining adjacent triangular patches which have a connection relation with the triangular patches corresponding to the initial triangular patch identifications according to the information topology of the triangular patches of the road surface.

In step S506, a target triangular patch to which a contact point between the tire and the road surface belongs at the next time is determined among the adjacent triangular patches.

Step S508, determining vertex coordinates of the target triangular patch and patch information of the target triangular patch based on the information topology of the target triangular patch.

And step S510, calculating a normal vector of the target triangular patch according to the vertex coordinates, and acquiring an axis vector of a coordinate system of the road surface.

In step S512, the coordinates of the contact point between the tire and the road surface are calculated based on the coordinate system and the patch information.

Step S514, generating information to be simulated of the target triangular patch based on the coordinates of the contact point and the normal vector.

And step S516, inputting the information to be simulated into the vehicle model dynamics integrator to solve the pose of the vehicle.

The vehicle pose determining method provided by the specification realizes rapid determination of the target pavement patch on the tiled pavement to realize accurate analysis of the pose of the vehicle, so that the coverage of a simulation test scene is improved, the determination rate of the pose cannot be influenced by scene change, and the detection capability of the vehicle in the current scene is effectively improved.

Corresponding to the above method embodiment, the present specification further provides a vehicle pose determining apparatus embodiment, and fig. 6 shows a schematic structural diagram of a vehicle pose determining apparatus provided in an embodiment of the present specification. As shown in fig. 6, the apparatus includes:

an obtaining identification module 602 configured to obtain a road surface patch identification corresponding to a position of a tire of a vehicle at a previous time;

a patch determining module 604 configured to determine a pavement patch having a connection relationship with the identified pavement patch;

an information determining module 606 configured to determine to-be-simulated information of a target pavement surface patch according to the pavement surface patches with the connection relationship;

a pose determination module 608 configured to determine pose information of the vehicle at the current time according to the information to be simulated of the target road surface patch.

In an alternative embodiment, different pavement patches have different information topologies, including but not limited to: the mark, the coordinate and the boundary point mark of the pavement surface patch are connected with each other;

the determine patch module 604 is further configured to:

In an optional embodiment, the determination information module 606 is further configured to:

obtaining boundary point marks corresponding to the road surface patches with the connection relation, and determining normal vectors; obtaining the coordinates of the intersection point of the tire coordinate system axis vector of the vehicle and the road surface patch with the connection relation; and taking the normal vector and the intersection point coordinate as information to be simulated.

In an optional embodiment, the obtain identification module 602 is further configured to:

obtaining the coordinates of the central point of the tire of the vehicle at the last moment; and determining the road surface patch projected by the central point coordinate, and determining the road surface patch identification of the road surface patch projected by the central point coordinate.

In an alternative embodiment, the pavement patches are triangles and the boundary point markers are triangle vertex markers.

determining a target pavement patch to which a contact point of a tire of the vehicle and a pavement belongs from the pavement patches with the connection relation according to a preset search strategy; and determining the information to be simulated of the target pavement surface patch.

In an optional embodiment, the pose determination module 608 is further configured to:

According to the vehicle pose determining device provided by the specification, after the road surface patch identification corresponding to the position of the tire of the vehicle at the previous moment is obtained, the road surface patch with the connection relation with the road surface patch of the identification can be determined, the information to be simulated of the target road surface patch is determined on the basis of the road surface patch with the connection relation, and finally the pose information of the vehicle at the current moment can be determined on the basis of the information to be simulated, so that the target road surface patch can be rapidly determined on a tiled road surface, the pose of the vehicle can be accurately analyzed, the coverage of a simulation test scene is improved, the determination rate of the pose cannot be influenced by scene change, and the detection capability of the vehicle under the current scene is effectively improved.

The above is an illustrative scheme of a vehicle pose determination apparatus of the present embodiment. It should be noted that the technical solution of the vehicle pose determining apparatus and the technical solution of the vehicle pose determining method belong to the same concept, and details of the technical solution of the vehicle pose determining apparatus, which are not described in detail, can be referred to the description of the technical solution of the vehicle pose determining method.

It should be noted that these algorithm modules (the above function modules) may be different according to the type of the autonomous vehicle. For example, different algorithm modules may be involved for logistics vehicles, public service vehicles, medical service vehicles, terminal service vehicles. The algorithm modules are illustrated below for these four autonomous vehicles, respectively:

the logistics vehicle refers to a vehicle used in a logistics scene, and may be, for example, a logistics vehicle with an automatic sorting function, a logistics vehicle with a refrigeration and heat preservation function, and a logistics vehicle with a measurement function. These logistics vehicles may involve different algorithm modules.

For example, the logistics vehicles can be provided with an automatic sorting device, and the automatic sorting device can automatically take out, convey, sort and store the goods after the logistics vehicles reach the destination. This relates to an algorithm module for sorting goods, which mainly implements logic control of goods taking out, carrying, sorting and storing.

For another example, in a cold chain logistics scenario, the logistics vehicle may further include a refrigeration and insulation device, and the refrigeration and insulation device may implement refrigeration or insulation of transported fruits, vegetables, aquatic products, frozen foods, and other perishable foods, so that the transportation environment is in a proper temperature environment, and the long-distance transportation problem of perishable foods is solved. The algorithm module is mainly used for dynamically and adaptively calculating the proper temperature of cold meal or heat preservation according to the information such as the property, the perishability, the transportation time, the current season, the climate and the like of food (or articles), and automatically adjusting the refrigerating and heat preservation device according to the proper temperature, so that a transporter does not need to manually adjust the temperature when the vehicle transports different foods or articles, the transporter is liberated from the complicated temperature regulation and control, and the refrigerating and heat preservation transportation efficiency is improved.

For another example, in most logistics scenarios, the fee is charged according to the volume and/or weight of the parcel, but the number of logistics parcels is very large, and the measurement of the volume and/or weight of the parcel by a courier is only dependent, which is very inefficient and has high labor cost. Therefore, in some logistics vehicles, a measuring device is additionally arranged, so that the volume and/or the weight of the logistics packages can be automatically measured, and the cost of the logistics packages can be calculated. This relates to an algorithm module for logistics package measurement, which is mainly used to identify the type of logistics package, determine the measurement mode of logistics package, such as volume measurement or weight measurement or combined measurement of volume and weight, and complete the volume and/or weight measurement according to the determined measurement mode, and complete the cost calculation according to the measurement result.

The public service vehicle is a vehicle providing some public service, and may be, for example, a fire truck, an ice removal truck, a watering cart, a snow scraper, a garbage disposal vehicle, a traffic guidance vehicle, and the like. These public service vehicles may involve different algorithm modules.

For example, in the case of an automatically driven fire fighting vehicle, the main task is to perform a reasonable fire fighting task on the fire scene, which involves an algorithm module for the fire fighting task, which at least needs to implement logic such as identification of the fire situation, planning of the fire fighting scheme, and automatic control of the fire fighting device.

For another example, for an ice removing vehicle, the main task is to remove ice and snow on the road surface, which involves an algorithm module for ice removal, the algorithm module at least needs to realize the recognition of the ice and snow condition on the road surface, formulate an ice removal scheme according to the ice and snow condition, such as which road sections need to be deiced, which road sections need not to be deiced, whether a salt spreading manner, the salt spreading gram number, and the like are adopted, and the logic of automatic control of a deicing device under the condition of determining the ice removal scheme.

The medical service vehicle is an automatic driving vehicle capable of providing one or more medical services, the vehicle can provide medical services such as disinfection, temperature measurement, dispensing and isolation, and the algorithm modules relate to algorithm modules for providing various self-service medical services.

The terminal service vehicle is a self-service type automatic driving vehicle which can replace some terminal devices to provide certain convenient service for users, and for example, the vehicles can provide services such as printing, attendance checking, scanning, unlocking, payment and retail for the users.

For example, in some application scenarios, a user often needs to go to a particular location to print or scan a document, which is time consuming and labor intensive. Therefore, a terminal service vehicle capable of providing printing/scanning services for users appears, the service vehicles can be interconnected with user terminal equipment, the users send out printing instructions through the terminal equipment, the service vehicles respond to the printing instructions, automatically print documents required by the users and automatically send the printed documents to the positions of the users, the users do not need to queue at a printer, and the printing efficiency can be greatly improved. Or, the scanning instruction sent by the user through the terminal equipment can be responded, the scanning vehicle is moved to the position of the user, the user finishes scanning on the scanning tool of the service vehicle on which the document to be scanned is placed, queuing at the printing/scanning machine is not needed, and time and labor are saved. This involves an algorithm module providing a print/scan service that needs to recognize at least the interconnection with the user terminal device, the response of the print/scan command, the positioning of the user's position, and the travel control.

For another example, as new retail items are developed, more and more electronic stores sell goods to large office buildings and public areas by means of self-service vending machines, but the self-service vending machines are placed at fixed positions and are not movable, and users need to go by the self-service vending machines to purchase the needed goods, which is still poor in convenience. Therefore, self-service driving vehicles capable of providing retail services appear, the service vehicles can carry commodities to move automatically and can provide corresponding self-service shopping APP or shopping entrances, a user can place an order for the self-service driving vehicles providing retail services through the APP or shopping entrances by means of a terminal such as a mobile phone, the order comprises names and quantities of commodities to be purchased, after the vehicle receives an order placing request, whether the current remaining commodities have the commodities purchased by the user and whether the quantities are enough can be determined, and under the condition that the commodities purchased by the user and the quantities are enough, the commodities can be carried to the user position automatically, and the commodities are provided for the user. This involves algorithm modules that provide retail services that essentially implement logic to respond to customer order requests, order processing, merchandise information maintenance, customer location, payment management, etc.

Fig. 7 illustrates a block diagram of a computing device 700 provided according to an embodiment of the present description. Components of the computing device 700 include, but are not limited to, a memory 710 and a processor 720. Processor 720 is coupled to memory 710 via bus 730, and database 750 is used to store data.

Computing device 700 also includes access device 740, access device 740 enabling computing device 700 to communicate via one or more networks 760. Examples of such networks include a public switched electrochemical network (PSTN), a Local Area Network (LAN), a Wide Area Network (WAN), a Personal Area Network (PAN), or a combination of communication networks such as the internet. Access device 740 may include one or more of any type of network interface (e.g., a Network Interface Card (NIC)) whether wired or wireless, such as an IEEE802.11 Wireless Local Area Network (WLAN) wireless interface, a worldwide interoperability for microwave access (Wi-MAX) interface, an ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a bluetooth interface, a Near Field Communication (NFC) interface, and so forth.

In one embodiment of the present description, the above-described components of computing device 700, as well as other components not shown in FIG. 7, may also be connected to each other, such as by a bus. It should be understood that the block diagram of the computing device structure shown in FIG. 7 is for purposes of example only and is not limiting as to the scope of the description. Other components may be added or replaced as desired by those skilled in the art.

The computing device 700 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., tablet computer, personal digital assistant, laptop computer, notebook computer, netbook, etc.), mobile e-mails (e.g., smart phones), wearable computing devices (e.g., smart watches, smart glasses, etc.), or other type of mobile device, or a stationary computing device such as a desktop computer or PC. Computing device 700 may also be a mobile or stationary server.

Wherein processor 720 is configured to execute the following computer-executable instructions:

The above is an illustrative scheme of a computing device of the present embodiment. It should be noted that the technical solution of the computing device and the technical solution of the vehicle pose determination method belong to the same concept, and details that are not described in detail in the technical solution of the computing device can be referred to the description of the technical solution of the vehicle pose determination method.

An embodiment of the present specification also provides a computer readable storage medium storing computer instructions that, when executed by a processor, are configured to:

determining the pavement surface patches which have a connection relation with the identified pavement surface patches;

The above is an illustrative scheme of a computer-readable storage medium of the present embodiment. It should be noted that the technical solution of the storage medium and the technical solution of the vehicle pose determination method belong to the same concept, and details that are not described in detail in the technical solution of the storage medium can be referred to the description of the technical solution of the vehicle pose determination method.

The foregoing description of specific embodiments has been presented for purposes of illustration and description. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

The computer instructions comprise computer program code which may be in source code form, object code form, an executable file or some intermediate form, or the like. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U.S. disk, removable hard disk, magnetic diskette, optical disk, computer Memory, read-Only Memory (ROM), random Access Memory (RAM), electrical carrier wave signal, telecommunications signal, and software distribution medium, etc. It should be noted that the computer-readable medium may contain suitable additions or subtractions depending on the requirements of legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer-readable media may not include electrical carrier signals or telecommunication signals in accordance with legislation and patent practice.

It should be noted that for simplicity and convenience of description, the above-described method embodiments are shown as a series of combinations of acts, but those skilled in the art will appreciate that the present description is not limited by the order of acts described, as some steps may occur in other orders or concurrently with other steps from the present description. Further, those skilled in the art will appreciate that the embodiments described in this specification are presently considered to be preferred embodiments and that acts and modules are not necessarily required to be described in this specification.

In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to the related descriptions of other embodiments.

The preferred embodiments of the present specification disclosed above are intended only to aid in the description of the specification. Alternative embodiments are not exhaustive and do not limit the invention to the precise embodiments described. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the specification and its practical application, to thereby enable others skilled in the art to best understand the specification and utilize the specification. The specification is limited only by the claims and their full scope and equivalents.

Claims

1. A vehicle pose determination method, comprising:

2. The method of claim 1, different pavement patches having different information topologies including, but not limited to: the mark, the coordinate and the boundary point mark of the pavement surface patch are connected with each other;

3. The method according to claim 2, wherein the determining the information to be simulated of the target pavement surface patch according to the pavement surface patches with the connection relationship comprises:

obtaining boundary point marks corresponding to the road surface patches with the connection relation, and determining normal vectors corresponding to the target road surface patches according to the boundary point marks;

4. The method of claim 1, wherein obtaining the pavement patch identification corresponding to the position of the tire of the vehicle at the previous time comprises:

5. The method of claim 2 or 3, the pavement patches being triangles, the boundary point identifiers being triangle vertex identifiers.

6. The method according to claim 1, wherein the determining the information to be simulated of the target pavement surface patch according to the pavement surface patches with the connection relationship comprises:

7. The method of claim 1, wherein the determining pose information of the vehicle at the current moment according to the information to be simulated of the target pavement patch comprises:

8. A vehicle pose determination apparatus comprising:

the information determining module is configured to determine to-be-simulated information of the target pavement surface patch according to the pavement surface patches with the connection relation;

9. A computing device, comprising:

a memory and a processor;

the memory is configured to store computer-executable instructions, and the processor is configured to execute the computer-executable instructions to implement the method of:

10. A computer-readable storage medium storing computer instructions which, when executed by a processor, implement the steps of the vehicle pose determination method of any one of claims 1 to 7.