CN114462225A - A rapid construction system for hybrid traffic simulation support environment under vehicle-road coordination - Google Patents

Abstract

The invention provides a rapid construction system for a hybrid traffic simulation support environment under vehicle-road coordination. The system includes: a hybrid traffic subject model library building module for constructing and storing moving object models in a hybrid traffic environment; a dynamic element model matching and extraction module for receiving dynamic object information collected by connected vehicles and intelligent roadside and scene information, draw the dynamic object simulation model, which is used to match the vehicle main body model with the highest similarity with the dynamic object simulation model, generate the optimal scene drawing sequence, and send the vehicle main body model and the optimal scene drawing sequence to the connected vehicle; The scene rendering and optimization module under the vehicle-road cooperative perception is used to generate the optimal scene rendering sequence of the main vehicle according to the vehicle main model and the optimal scene rendering sequence. The invention can provide a simulation verification environment for the function test of the vehicle-road coordination system, and has great significance for improving the simulation efficiency of the vehicle-road coordination system, reducing the test cost and promoting the technology.

Description

A rapid construction system for hybrid traffic simulation support environment under vehicle-road coordination

technical field

The invention relates to the technical field of traffic simulation, in particular to a rapid construction system for a hybrid traffic simulation support environment under vehicle-road coordination.

Background technique

Under the support of increasingly mature vehicle-road collaboration technology, the information interaction and sharing capabilities between vehicles are enhanced, and the traditional traffic environment dominated by human-driven vehicles is changing to a mixture of artificial/intelligent/connected/intelligent connected vehicles. In the new hybrid traffic environment, there are many typical types of hybrid traffic and their performance is complex. Frequent information interaction between vehicles such as vehicles and vehicles, vehicles and roads, and complex motion trends between vehicles are difficult to provide real-time visualization only by previous simulations. The virtual visualization simulation technology, which has been widely used in recent years, can timely display and feedback the simulation results in an all-round way, and has been widely used in aviation, navigation, railway, automatic control simulation and other fields. into a more practical simulation method.

The real-time and rapid construction of virtual traffic environment is an important step in the simulation of intelligent traffic virtual scene. Traditional simulation environment generation often adopts artificial generation method. According to aerial map or satellite map, the simulation environment is produced by hand-painting. Although this method is simple to operate, but There are many shortcomings, such as poor drawing accuracy, low drawing efficiency, and poor reproducibility. In view of this situation, how to quickly build a reliable, credible and efficient hybrid traffic simulation environment in the case of rapid changes in the traffic environment, reproduce huge and complex real traffic scenarios, provide users with rapid environmental visualization services, and help realize vehicle-road collaboration. Preliminary performance evaluation and functional verification of the system, improving simulation efficiency, reducing test costs and technology promotion are of great significance.

At present, there is no rapid construction method that can provide users with a hybrid traffic simulation support environment under vehicle-road coordination.

SUMMARY OF THE INVENTION

The embodiments of the present invention provide a rapid construction system for a hybrid traffic simulation support environment under vehicle-road coordination, so as to realize an adaptive hybrid traffic environment collaborative construction method.

In order to achieve the above objects, the present invention adopts the following technical solutions.

A hybrid traffic simulation support environment rapid construction system under vehicle-road collaboration, comprising: a hybrid traffic subject model library building module, a dynamic element model matching and extraction module, and a vehicle-road collaborative perception scene rendering and optimization module;

The hybrid traffic subject model library building module is used to construct and store moving object models in the mixed traffic environment, and provide a hierarchical index of the model, and the moving objects include vehicle subjects of different intelligence levels;

The matching and extraction module of the dynamic element model is used to receive the dynamic object information and scene information collected by the connected vehicle and the intelligent roadside, draw the dynamic object simulation model, and match the dynamic object simulation model in the mixed traffic subject model library. The vehicle main body model with the highest model similarity generates the optimal scene drawing sequence according to the received scene information, and sends the vehicle main body model and the optimal scene drawing sequence to the connected vehicle;

The described scene drawing and optimization module under vehicle-road cooperative perception is used to generate the optimal scene drawing sequence of the main vehicle of the connected vehicle according to the received vehicle main model and the optimal scene drawing sequence, and draw the optimal scene of the main vehicle. The sequence is sent to other connected vehicles around.

Preferably, the hybrid traffic subject model library building module and the dynamic element model matching and extraction module are set in the data center, and the scene rendering and optimization module under vehicle-road collaborative perception is set in the connected vehicle.

Preferably, the hybrid traffic subject model library building module is specifically used for classifying and storing moving object models through multimedia database technology, decomposing each moving object into model primitives, and collocating the behavioral characteristic logic of different moving objects, to detect the main vehicle The intelligent level, model and purpose of the vehicle are classified, organized and managed, and the vehicle elements are analyzed by the AHP method, and the vehicle is decomposed into several levels of model primitives to form an interrelated and affiliated hierarchical structure model index. Moving object model index table.

Preferably, the matching and extraction module of the dynamic element model is specifically used to obtain environmental information through intelligent roadside equipment and other connected intelligent vehicles, to organically segment and reshape the environmental data, and to extract typical hierarchical structure features, Generate the optimal scene drawing sequence; also obtain dynamic object information through the vehicle and roadside environment perception units, perform preliminary block data dimension reduction, segmentation processing and reconstruction for the dynamic object information, and then extract the hierarchical structure features of dynamic objects in each block, Draw the dynamic object simulation model, and use the feature correlation function to match the moving object model with the highest similarity with the dynamic object simulation model in the mixed traffic subject model library.

Preferably, the scene drawing and optimization module under vehicle-road collaborative perception is specifically configured to generate a main vehicle drawing sequence according to the received vehicle main body model, and generate a matching and extraction module for the received other connected vehicles and dynamic element models. The optimal scene rendering sequence is based on time synchronization and reliability judgment of the main vehicle rendering sequence generated by itself, and then the received information is divided into sequence slices, cross-validated and optimized for the redundant region rendering sequence, and combined to verify the remaining rendering region sequence. , using the adaptive scene drawing sequence optimization function to generate the optimal scene drawing sequence of the main vehicle at the current moment of the main vehicle, and sending the optimal scene drawing sequence of the main vehicle to other connected vehicles on the same planned path through the wireless network.

Preferably, the scene rendering and optimization module under vehicle-road cooperative perception is specifically used to generate the optimal scene rendering sequence of the main vehicle. The length of each slice sequence is determined by the optimal simulation step size of the rendering unit, and each initial scene rendering The sequence will be determined according to the result of the last sequence optimization. The optimization index set is composed of drawing time, information redundancy, information reliability, environment coverage, environment fit and scene drawing balance. The index weight is based on the complexity of different scenarios. The importance of the indicators designed below is preferred to be dynamically adjusted.

It can be seen from the technical solutions provided by the above embodiments of the present invention that the present invention can provide a simulation verification environment for the function test of the vehicle-road coordination system, which is of great significance for improving the simulation efficiency of the vehicle-road coordination system, reducing the test cost and promoting the technology.

Additional aspects and advantages of the present invention will be set forth in part in the following description, which will be apparent from the following description, or may be learned by practice of the present invention.

Description of drawings

In order to illustrate the technical solutions of the embodiments of the present invention more clearly, the following briefly introduces the accompanying drawings used in the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained from these drawings without any creative effort.

1 is a schematic diagram of an implementation of a rapid construction system for a hybrid traffic simulation support environment under vehicle-road coordination provided by an embodiment of the present invention;

FIG. 2 is a processing flowchart of a scene rendering sequence collaborative generation module under vehicle-road collaborative perception provided by an embodiment of the present invention.

Detailed ways

Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, but not to be construed as a limitation of the present invention.

It will be understood by those skilled in the art that the singular forms "a", "an", "the" and "the" as used herein can include the plural forms as well, unless expressly stated otherwise. It should be further understood that the word "comprising" used in the description of the present invention refers to the presence of stated features, integers, steps, operations, elements and/or components, but does not exclude the presence or addition of one or more other features, Integers, steps, operations, elements, components and/or groups thereof. It will be understood that when we refer to an element as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Furthermore, "connected" or "coupled" as used herein may include wirelessly connected or coupled. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.

It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It should also be understood that terms such as those defined in general dictionaries should be understood to have meanings consistent with their meanings in the context of the prior art and, unless defined as herein, are not to be taken in an idealized or overly formal sense. explain.

In order to facilitate the understanding of the embodiments of the present invention, the following will take several specific embodiments as examples for further explanation and description in conjunction with the accompanying drawings, and each embodiment does not constitute a limitation to the embodiments of the present invention.

A schematic diagram of the realization of a system for rapidly constructing a hybrid traffic simulation support environment under vehicle-road coordination provided by an embodiment of the present invention is shown in FIG. 1 . Unit), detection equipment, data center and other objects are completed together, including: hybrid traffic subject model library building module, dynamic element model matching and extraction module and vehicle-road collaborative perception scene rendering and optimization module.

The hybrid traffic subject model library building module is used for constructing and storing moving object models in the hybrid traffic environment, and providing a hierarchical index of the models. The above-mentioned moving objects include vehicle bodies of different intelligence levels, and the moving object models are organized and managed hierarchically; this module is set in the data center.

The matching and extraction module of the dynamic element model is used to receive dynamic object information and scene information collected by the connected vehicle and the intelligent roadside, perform data processing and analysis on the dynamic object information, extract the hierarchical structure features of the dynamic object, and draw the dynamic object information. The dynamic object simulation model uses the feature correlation function to match the vehicle main body model with the highest similarity to the dynamic object simulation model in the mixed traffic main body model library, and generates the optimal scene drawing sequence according to the received scene information. The matching vehicle body model and related model features, and the optimal scene drawing sequence are sent to the connected vehicle. The module is set up in the data center.

The described scene rendering and optimization module under vehicle-road cooperative perception is used to generate the optimal scene rendering sequence of the main vehicle of the connected vehicle based on the adaptive scene rendering sequence optimization function according to the received vehicle body model and the optimal scene rendering sequence, And send the optimal scene rendering sequence to other connected vehicles around. The optimal scene rendering sequence sent by other surrounding connected vehicles and the main vehicle rendering sequence are combined for verification. The module is installed on the connected vehicle.

Specifically, the above-mentioned hybrid traffic subject model library building module is used to construct and store moving object models in a hybrid traffic environment. The hybrid traffic subject model library uses multimedia database technology to classify and store moving object models. The above moving objects are traffic participants with multiple intelligence levels such as artificial/networked/intelligent connected vehicles. The hybrid traffic subject model library includes decomposing each complex object. It is a simple, microscopic and operable model primitive, and is matched with the behavioral characteristic logic of different moving objects to solve the characterization problem of different intelligence levels, various forms and different configurations of vehicle subjects in mixed traffic scenes. The various types of vehicle models are simple models with rigid body characteristics and no texture, and are composed of simple geometric shapes such as spheres, capsules, boxed shapes, and polygons. and management.

The above-mentioned hybrid traffic subject model library classifies, organizes and manages the intelligence level, model and purpose of the subject vehicle, and analyzes the vehicle elements through the AHP method, and decomposes the vehicle into several levels of model primitives to form an interrelated and Hierarchical model index with affiliation. At the same time, a common index table is also constructed to store the combination of vehicle models and other models that are frequently used in operating scenarios, so as to realize rapid model call in different traffic operating environments.

The matching and extraction module of the dynamic element model is mainly aimed at dynamic moving objects. It obtains dynamic object information through on-board and roadside environment perception units (cameras, lidars, radars, etc.), and analyzes the geometric parameters and motion of dynamic objects. Information processing and association matching are performed on the state information. It also obtains more environmental information through intelligent roadside equipment and other connected intelligent vehicles, including the beyond-horizon environment information outside its own perception area, and organically divides and reshapes the environmental data in a unified format data structure to extract typical Hierarchical features to generate optimal scene rendering sequences. Then, according to the multi-dimensional features of the main body of the vehicle and the vehicle hierarchy, the dynamic object information is subjected to preliminary block data dimension reduction, segmentation processing and reconstruction, and then the hierarchical structure features of the dynamic objects in each block are extracted, and the dynamic object simulation model is drawn. The moving object model with the highest similarity with the dynamic object simulation model is matched in the hybrid traffic subject model library using the feature correlation function. The feature weights of the feature correlation function can be trained offline through feature data fitting and neural network.

The scene rendering and optimization module under vehicle-road cooperative perception is used to generate a scene rendering sequence in a mixed scene, and perform rendering optimization on the scene rendering sequence. FIG. 2 shows a processing flow chart of a scene rendering sequence collaborative generation module under vehicle-road collaborative perception provided by an embodiment of the present invention. The subject vehicle receives the optimal scene rendering sequence generated by other connected vehicles and intelligent roadside in a good communication environment, and after time synchronization and reliability judgment with the subject vehicle rendering sequence generated by itself, the received information is divided into sequence slices , cross-validate and optimize the redundant area drawing sequence, combine and verify the remaining drawing area sequence, and finally generate the optimal scene drawing sequence of the main vehicle at the current moment of the main vehicle, and send the optimal scene drawing sequence of the main vehicle to other same planned paths through the wireless network In order to optimize the update speed of moving objects in its virtual traffic environment, and realize the coordination, accuracy, comprehensiveness and rapidity of the drawing sequence.

The optimal scene rendering sequence of the subject vehicle is determined and generated by an adaptive scene rendering sequence optimization function, and the length of each slice sequence is determined by the optimal simulation step size of the rendering unit, and each initial scene rendering sequence will be optimized according to the previous sequence. As a result, the optimization index set is composed of drawing time, information redundancy, information reliability, environmental coverage, environmental fit and scene drawing balance. Dynamic Adjustment.

During the scene rendering process of the scene rendering and optimization module under the described vehicle-road collaborative perception, the detected new dynamic object will be targeted and tracked, the dynamic object simulation model will be drawn, and it will be stored as a new node. When drawing, you only need to dynamically update the model position; for other static real objects, use offline generation to build the road network and surrounding buildings in advance, when drawing the scene, determine the road centerline based on the Cartesian coordinate system frame, and Based on the Frenet coordinate frame, the road geometry is decomposed, and the road node topology connection model is established. Then, the interactive geometric shape mapping method is used to incrementally draw the road from the road centerline to the nodes on the two side lanes and the road boundary. And the objects in the non-target path planning area are reduced by 3D redundant surface.

The sequence optimization in the scene rendering and optimization module under the vehicle-road collaborative perception is mainly to construct an adaptive scene rendering sequence optimization function to optimize the sequence of environment rendering and dynamic object state update, and perform vehicle-road rendering sequence collaboration under the support of the Internet of Vehicles. Process and combine to improve the accuracy and coverage of virtual traffic environment construction. Since the motion states of surrounding vehicles collected under vehicle motion are continuous, each initial sequence will be determined according to the results of the previous sequence optimization, and the index weight of the collaborative sequence optimization function will be determined according to different The importance of the indicators designed under the scene complexity prefers to be dynamically adjusted to save computing resources. Next, extract the model according to the environment drawing sequence to draw the scene. During the drawing process, different drawing strategies are used for different objects. Dynamic objects use the behavior feature logic assigned by the model library to track targets, and only need to update their 3D graphics positions after the initial drawing; other static object models are generated offline. When drawing, the road only needs to use the Frenet coordinate system. The horizontal and vertical parameters express the advantages of the road structure, reduce the calculation of the curvature of the road when drawing, and reduce the three-dimensional redundant surface of other objects to simplify the drawing process of the non-important model.

To sum up, the embodiments of the present invention provide a rapid construction system for a hybrid traffic simulation support environment under the coordination of vehicles and roads, which realizes the adaptive construction of a hybrid traffic simulation support environment under the coordination of multiple intelligent traffic subjects, and can solve the inability of traditional environment construction methods. The shortcomings of multi-directional real-time acquisition of traffic operation status can effectively improve the rendering efficiency, accuracy and coverage of traffic simulation environment construction, reproduce huge and complex real traffic scenes, and implement preliminary performance evaluation and functional verification of vehicle-road coordination systems. Simulation efficiency, reducing test costs and technology promotion are of great significance.

Those of ordinary skill in the art can understand that the accompanying drawing is only a schematic diagram of an embodiment, and the modules or processes in the accompanying drawing are not necessarily necessary to implement the present invention.

From the description of the above embodiments, those skilled in the art can clearly understand that the present invention can be implemented by means of software plus a necessary general hardware platform. Based on this understanding, the technical solutions of the present invention can be embodied in the form of software products in essence or the parts that make contributions to the prior art. The computer software products can be stored in storage media, such as ROM/RAM, magnetic disks, etc. , CD, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of the present invention.

Each embodiment in this specification is described in a progressive manner, and the same and similar parts between the various embodiments may be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the apparatus or system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and reference may be made to some descriptions of the method embodiments for related parts. The apparatus and system embodiments described above are only illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, It can be located in one place, or it can be distributed over multiple network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution in this embodiment. Those of ordinary skill in the art can understand and implement it without creative effort.

The above description is only a preferred embodiment of the present invention, but the protection scope of the present invention is not limited to this. Substitutions should be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims (6)

1. A hybrid traffic simulation support environment rapid construction system under vehicle-road cooperation is characterized by comprising the following components: the system comprises a hybrid traffic subject model base construction module, a dynamic element model matching and extracting module and a scene drawing and optimizing module under cooperative vehicle and road perception;

the hybrid traffic subject model library construction module is used for constructing and storing a moving object model in a hybrid traffic environment and providing a model hierarchical index, wherein the moving object comprises vehicle subjects with different intelligent levels;

the matching and extracting module of the dynamic element model is used for receiving dynamic object information and scene information collected by the internet-connected vehicle and the intelligent roadside, drawing a dynamic object simulation model, matching a vehicle main body model with the highest similarity to the dynamic object simulation model in the mixed traffic main body model library, generating an optimal scene drawing sequence according to the received scene information, and sending the vehicle main body model and the optimal scene drawing sequence to the internet-connected vehicle;

and the scene drawing and optimizing module under the cooperative vehicle-road perception is used for generating a main vehicle optimal scene drawing sequence of the networked vehicle according to the received vehicle main model and the optimal scene drawing sequence and sending the main vehicle optimal scene drawing sequence to other surrounding networked vehicles.

2. The system of claim 1, wherein the hybrid traffic subject model library construction module and the dynamic element model matching and extracting module are arranged in a data center, and the scene drawing and optimizing module under the cooperative vehicle-road perception is arranged in an internet vehicle.

3. The system of claim 1, wherein the hybrid transportation subject model base building module is specifically configured to store moving object models by classification through a multimedia database technology, decompose each moving object into model primitives, and perform classification organization and management on intelligence level, model number and usage of a subject vehicle by matching with behavioral characteristic logic of different moving objects, analyze vehicle elements through a hierarchical analysis method, decompose vehicles into model primitives of multiple levels, form a hierarchical structure model index associated with each other and having a membership relationship, and build a moving object model index table.

4. The system according to claim 1, wherein the matching and extracting module of the dynamic element model is specifically configured to acquire environmental information through an intelligent roadside device and other networked intelligent vehicles, perform organic segmentation and remodeling on environmental data, extract typical hierarchical structure features, and generate an optimal scene drawing sequence; and obtaining dynamic object information through the vehicle-mounted and road-side environment sensing units, performing preliminary block data dimension reduction, segmentation processing and reconstruction on the dynamic object information, extracting the hierarchical structure characteristics of the dynamic objects in each block, drawing a dynamic object simulation model, and matching a moving object model with the highest similarity to the dynamic object simulation model in the mixed traffic main body model library by using a characteristic association function.

5. The system according to claim 1, wherein the scene drawing and optimizing module under the cooperative vehicle-road perception is specifically configured to generate a main vehicle drawing sequence according to a received vehicle main model, perform time synchronization and reliability discrimination on the received optimal scene drawing sequence generated by the matching and extraction module of other internet vehicles and the dynamic element model and the main vehicle drawing sequence generated by the optimal scene drawing sequence, perform sequence slice division on the received information, cross-verify and optimize the redundant region drawing sequence, perform combined verification on the remaining drawing region sequence, generate the main vehicle optimal scene drawing sequence of the main vehicle at the current time by using an adaptive scene drawing sequence optimization function, and send the main vehicle optimal scene drawing sequence to the internet vehicles on the same other planned paths through a wireless network.

6. The system according to claim 5, wherein the scene drawing and optimizing module under cooperative vehicle-road perception specifically determines the length of each section of a slice sequence of a generated optimal scene drawing sequence of the subject vehicle according to the optimal simulation step length of a drawing unit, each initial scene drawing sequence is determined according to the last sequence optimization result, the optimization index set is composed of drawing time consumption, information redundancy, information reliability, environmental coverage, environmental fitness and scene drawing balance, and the index weight is dynamically adjusted according to the preference of the importance degree of the index designed under different scene complexities.

Images