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

Abstract

The present invention provides a system for rapidly constructing a hybrid traffic simulation support environment under vehicle-road collaboration. The system includes: a hybrid traffic subject model library construction module, which is used to construct and store motion object models in a hybrid traffic environment; a dynamic element model matching and extraction module, which is used to receive dynamic object information and scene information collected by networked vehicles and intelligent roadsides, draw dynamic object simulation models, match the vehicle subject model with the highest similarity to the dynamic object simulation model, generate an optimal scene drawing sequence, and send the vehicle subject model and the optimal scene drawing sequence to the networked vehicle; a scene drawing and optimization module under vehicle-road collaborative perception, which is used to generate the optimal scene drawing sequence of the subject vehicle according to the vehicle subject model and the optimal scene drawing sequence. The present invention can provide a simulation verification environment for the functional testing of the vehicle-road collaborative system, which is of great significance for improving the simulation efficiency of the vehicle-road collaborative system, reducing testing costs and promoting technology.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic simulation, and in particular to a system for quickly constructing a hybrid traffic simulation support environment under vehicle-road collaboration. Background Art

[0002] Supported by increasingly mature vehicle-road collaborative technology, the information interaction and sharing capabilities between vehicles are enhanced. The traditional traffic environment dominated by manually driven vehicles is transforming into a new mixed traffic environment where manual / intelligent / networked / intelligently networked vehicles are mixed. There are many typical scene types for mixed traffic and they are complex in expression. The frequent information interaction behaviors between vehicle-to-vehicle, vehicle-to-road and other equipment and the complex movement trends between vehicles are difficult to give real-time and intuitive graphical representations based on previous simulations. The virtual visualization simulation technology that has been widely used in recent years can timely display and feedback the simulation results in all directions in three dimensions, and has been widely used in aviation, navigation, railways, automatic control simulation and other fields, and has become a relatively practical simulation method.

[0003] Real-time and rapid construction of virtual traffic environment is an important step in the simulation of intelligent traffic virtual scenes. Traditional simulation environment generation often adopts artificial generation methods, and the simulation environment is hand-drawn according to aerial maps or satellite maps. Although this method is simple to operate, it has many shortcomings, such as poor drawing accuracy, low drawing efficiency, and poor reproducibility. In view of this situation, how to quickly build a reliable, trustworthy, and efficient mixed traffic simulation environment in the case of rapid changes in the traffic environment, reproduce large and complex real traffic scenes, and provide users with rapid environment visualization services is of great significance to the realization of preliminary performance evaluation and functional verification of vehicle-road cooperative systems, improve simulation efficiency, reduce test costs, and promote technology.

[0004] At present, there is no method that can provide users with a rapid construction method for a mixed traffic simulation support environment under vehicle-road collaboration. Summary of the invention

[0005] An embodiment of the present invention provides a system for quickly constructing a hybrid traffic simulation support environment under vehicle-road collaboration to implement a method for collaboratively constructing an adaptive hybrid traffic environment.

[0006] In order to achieve the above object, the present invention adopts the following technical scheme.

[0007] A system for rapidly constructing a hybrid traffic simulation support environment under vehicle-road collaboration, including: a hybrid traffic subject model library construction module, a dynamic element model matching and extraction module, and a scene rendering and optimization module under vehicle-road collaboration perception;

[0008] The mixed traffic subject model library construction module is used to construct and store the moving object model in the mixed traffic environment and provide a hierarchical index of the model, wherein the moving object includes vehicle subjects of different intelligence levels;

[0009] The dynamic element model matching and extraction module is used to receive dynamic object information and scene information collected by the connected vehicle and the intelligent roadside, draw a dynamic object simulation model, match the vehicle subject model with the highest similarity to the dynamic object simulation model in the mixed traffic subject model library, generate an optimal scene drawing sequence according to the received scene information, and send the vehicle subject model and the optimal scene drawing sequence to the connected vehicle;

[0010] The 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 send the optimal scene drawing sequence of the main vehicle to other connected vehicles around it.

[0011] Preferably, the mixed traffic subject model library construction module and the dynamic element model matching and extraction module are set in the data center, and the scene drawing and optimization module under vehicle-road collaborative perception is set in the connected vehicle.

[0012] Preferably, the mixed traffic subject model library construction module is specifically used to classify and store motion object models through multimedia database technology, decompose each motion object into model primitives, and classify and organize and manage the intelligence level, model and purpose of the subject vehicle in combination with the behavioral characteristic logic of different motion objects, analyze the vehicle elements through the hierarchical analysis method, decompose the vehicle into several levels of model primitives, form a hierarchical model index that is interrelated and has a subordinate relationship, and construct a motion object model index table.

[0013] Preferably, the matching and extraction module of the dynamic element model is specifically used to obtain environmental information through intelligent roadside equipment and other networked intelligent vehicles, organically divide and reshape the environmental data, extract typical hierarchical features, and generate an optimal scene drawing sequence; it also obtains dynamic object information through vehicle-mounted and roadside environmental perception units, performs preliminary block data dimensionality reduction, segmentation processing and reconstruction on the dynamic object information, and then extracts the hierarchical features of the dynamic objects in each block, draws a dynamic object simulation model, and uses the feature correlation function to match the moving object model with the highest similarity to the dynamic object simulation model in the mixed traffic subject model library.

[0014] Preferably, the scene drawing and optimization module under vehicle-road collaborative perception is specifically used to generate a subject vehicle drawing sequence according to the received vehicle subject model, synchronize the time and credibility of the optimal scene drawing sequence generated by the matching and extraction module of other connected vehicles and dynamic element models received with the subject vehicle drawing sequence generated by itself, perform sequence slicing on the received information, cross-validate and optimize the redundant area drawing sequences, combine and verify the remaining drawing area sequences, use the adaptive scene drawing sequence optimization function to generate the optimal scene drawing sequence of the subject vehicle at the current moment, and send the optimal scene drawing sequence of the subject vehicle to other connected vehicles on the same planned path through the wireless network.

[0015] Preferably, the scene drawing and optimization module under vehicle-road cooperative perception is specifically used to generate the optimal scene drawing sequence of the main vehicle. The length of each slice sequence is determined by the optimal simulation step of the drawing unit. Each initial scene drawing sequence will be determined according to the result of the previous sequence optimization. The optimization index set is composed of drawing time, information redundancy, information credibility, environmental coverage, environmental fit and scene drawing balance. The index weight is dynamically adjusted according to the index importance preference designed under different scene complexities.

[0016] It can be seen from the technical solutions provided by the above-mentioned embodiments of the present invention that the present invention can provide a simulation verification environment for the functional testing of the vehicle-road cooperative system, which is of great significance for improving the simulation efficiency of the vehicle-road cooperative system, reducing testing costs and promoting technology.

[0017] Additional aspects and advantages of the present invention will be given in part in the following description, which will become obvious from the following description, or may be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0019] Figure 1 A schematic diagram of a system for rapidly constructing a hybrid traffic simulation support environment under vehicle-road collaboration provided by an embodiment of the present invention;

[0020] Figure 2 A processing flow chart of a scene rendering sequence collaborative generation module under vehicle-road collaborative perception provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0021] The embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be interpreted as limiting the present invention.

[0022] It will be understood by those skilled in the art that, unless expressly stated, the singular forms "one", "said", and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present invention refers to the presence of the 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 should be understood that when we refer to an element as being "connected" or "coupled" to another element, it may be directly connected or coupled to the other element, or there may be intermediate elements. In addition, the "connection" or "coupling" used herein may include wireless connection or coupling. The term "and / or" used herein includes any unit and all combinations of one or more associated listed items.

[0023] 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 those generally understood by those skilled in the art in the art to which the present invention belongs. It should also be understood that terms such as those defined in common dictionaries should be understood to have meanings consistent with the meanings in the context of the prior art, and will not be interpreted with idealized or overly formal meanings unless defined as herein.

[0024] To facilitate understanding of the embodiments of the present invention, several specific embodiments will be further explained below with reference to the accompanying drawings, and each embodiment does not constitute a limitation on the embodiments of the present invention.

[0025] The implementation principle diagram of a system for rapidly constructing a hybrid traffic simulation support environment under vehicle-road collaboration provided by an embodiment of the present invention is as follows: Figure 1 As shown, the processing process of the system will be completed jointly by connected vehicles, RSU (Road Side Unit), detection equipment, data center and other objects, including: a mixed traffic subject model library construction module, a dynamic element model matching and extraction module and a scene drawing and optimization module under vehicle-road collaborative perception.

[0026] The mixed traffic subject model library construction module is used to construct and store the moving object model in the mixed traffic environment and provide a hierarchical index of the model. The moving objects include vehicle subjects of different intelligence levels, and the moving object models are hierarchically classified, organized and managed; this module is set in the data center.

[0027] The dynamic element model matching and extraction module is used to receive dynamic object information and scene information collected by the networked vehicle and the intelligent roadside, perform data processing and analysis on the dynamic object information, extract the hierarchical structure features of the dynamic object, draw the dynamic object simulation model, use the feature association function to match the vehicle subject model with the highest similarity to the drawn dynamic object simulation model in the mixed traffic subject model library, and generate the optimal scene drawing sequence according to the received scene information. The matched vehicle subject model and related model features and the optimal scene drawing sequence are sent to the networked vehicle. This module is set in the data center.

[0028] The 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 based on the received vehicle main body model and the optimal scene drawing sequence based on the adaptive scene drawing sequence optimization function, and send the optimal scene drawing sequence to other connected vehicles around. The optimal scene drawing sequence sent by other connected vehicles around is combined and verified with the main vehicle drawing sequence. This module is set on the connected vehicle.

[0029] Specifically, the above-mentioned mixed traffic subject model library construction module is used to construct and store the moving object model in the mixed traffic environment. The mixed traffic subject model library stores the moving object model by classification through multimedia database technology. The above-mentioned moving objects are traffic participants of multiple intelligence levels such as artificial / networked / intelligent networked vehicles. The mixed traffic subject model library contains simple, microscopic and operable model primitives after decomposing each complex object, and is matched with the behavioral characteristic logic of different moving objects to solve the characterization problem of different intelligence levels, various forms and configurations of vehicle subjects in mixed traffic scenes. The various types of vehicle models are simple models with rigid body characteristics and no texture, which are composed of a combination of simple geometric shapes such as spheres, capsules, boxed shapes, polygons, etc. At the same time, the mixed traffic subject model library is hierarchically classified, organized and managed for simulation models.

[0030] The above-mentioned hybrid traffic subject model library classifies, organizes and manages the intelligence level, model and purpose of the subject vehicles. It also analyzes the vehicle elements through the hierarchical analysis method, decomposes the vehicle into several levels of model primitives, and forms a hierarchical model index with mutual correlation and affiliation. At the same time, it also constructs a common index table to store frequently used vehicle models and other model combinations in operation scenarios, so as to realize the rapid call of models in different traffic operation environments.

[0031] The matching and extraction module of the dynamic element model is mainly aimed at dynamic moving objects. It obtains dynamic object information through vehicle-mounted and roadside environmental perception units (cameras, lidars, radars, etc.), and performs information processing and correlation matching on the geometric parameters and motion state information of dynamic objects. It also obtains more environmental information through intelligent roadside equipment and other networked intelligent vehicles, including beyond-visual-range environmental information outside its own perception area, and organically divides and reshapes the environmental data in a unified format data structure, extracts typical hierarchical features, and generates an optimal scene drawing sequence. Then, according to the multi-dimensional characteristics of the vehicle-road subject and the vehicle hierarchy, the dynamic object information is preliminarily reduced in block data, segmented and reconstructed, and then the hierarchical features of the dynamic objects in each block are extracted to draw a dynamic object simulation model. The feature association function is used to match the moving object model with the highest similarity to the dynamic object simulation model in the mixed traffic subject model library. The feature weights of the feature association function can be trained offline through feature data fitting and neural networks.

[0032] The scene rendering and optimization module under vehicle-road cooperative perception is used to generate a scene rendering sequence under a mixed scene and optimize the scene rendering sequence. Figure 2 As shown. In a good communication environment, the subject vehicle receives the optimal scene drawing sequence generated by other connected vehicles and intelligent roadside, synchronizes the time with the subject vehicle drawing sequence generated by itself and determines the credibility, then divides the received information into sequence slices, cross-validates and optimizes the redundant area drawing sequence, combines and verifies the remaining drawing area sequence, and finally generates the subject vehicle's optimal scene drawing sequence at the current moment. The subject vehicle's optimal scene drawing sequence is sent to other connected vehicles on the same planned path through a wireless network to optimize the update speed of moving objects in their virtual traffic environment and achieve the coordination, accuracy, comprehensiveness and speed of the drawing sequence.

[0033] The optimal scene drawing sequence of the subject vehicle is generated by an adaptive scene drawing sequence optimization function, and the length of each slice sequence is determined by the optimal simulation step of the drawing unit. Each initial scene drawing sequence will be determined according to the result of the previous sequence optimization. The optimization index set is composed of drawing time, information redundancy, information credibility, environmental coverage, environmental fit and scene drawing balance. The index weight is dynamically adjusted according to the index importance preference designed under different scene complexities.

[0034] During the scene drawing process of the scene drawing and optimization module under the vehicle-road cooperative perception, target association and tracking will be performed on the newly detected dynamic objects, and the simulation model of the dynamic object will be drawn and stored as a new node. In the subsequent drawing, only the model position needs to be dynamically updated; for other static real objects, the road network and surrounding buildings are constructed in advance by offline generation. When drawing the scene, the road centerline is determined based on the Cartesian coordinate system framework, and the road geometry is decomposed based on the Frenet coordinate system framework, and a road node topological 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 of the lanes on both sides and the road boundaries; three-dimensional redundant surfaces are reduced for objects in remote traffic areas and non-target path planning areas.

[0035] The sequence optimization in the scene rendering and optimization module under vehicle-road cooperative perception mainly builds an adaptive scene rendering sequence optimization function to optimize the order of environment rendering and dynamic object state update, and performs vehicle-road rendering sequence collaborative processing and combination under the support of the Internet of Vehicles to improve the accuracy and coverage of virtual traffic environment construction. Since the motion state of surrounding vehicles collected under vehicle motion is continuous, each initial sequence will be determined according to the result of the previous sequence optimization. The weight of the collaborative sequence optimization function index is dynamically adjusted according to the index importance preference designed under different scene complexities to save computing resources. Next, the model is extracted according to the environment rendering sequence for scene rendering. During the rendering process, different rendering strategies are adopted for different objects. Dynamic objects use the behavioral feature logic assigned to them by the model library for target tracking. After the initial rendering, only their three-dimensional graphic position needs to be updated; other static object models are generated offline. When drawing, the road uses the Frenet coordinate system to express the advantages of the road structure with only horizontal and vertical parameters, which reduces the calculation of curvature when drawing the road. Other objects perform three-dimensional redundant surface reduction to simplify the rendering process of non-important models.

[0036] To sum up, the embodiments of the present invention provide a system for quickly constructing a hybrid traffic simulation support environment under vehicle-road collaboration, which can realize the adaptive construction of a hybrid traffic simulation support environment under the collaboration of multiple intelligent traffic entities. It can solve the shortcomings of traditional environment construction methods that cannot obtain traffic operation status in real time from multiple directions. It can effectively improve the drawing efficiency, accuracy and coverage of traffic simulation environment construction, and reproduce large and complex real traffic scenes. It is of great significance to realize the preliminary performance evaluation and function verification of the vehicle-road collaboration system, improve simulation efficiency, reduce testing costs and promote technology.

[0037] Those skilled in the art can understand that the accompanying drawings are only schematic diagrams of an embodiment, and the modules or processes in the accompanying drawings are not necessarily required to implement the present invention.

[0038] It can be known from the description of the above implementation methods that 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 such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present invention or certain parts of the embodiments.

[0039] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. The device and system embodiments described above are merely schematic, 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, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0040] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A system for rapidly constructing a hybrid traffic simulation support environment under vehicle-road collaboration, characterized in that: include: The mixed traffic subject model library construction module, the dynamic element model matching and extraction module, and the vehicle-road cooperative perception scene rendering and optimization module; The mixed traffic subject model library construction module is used to construct and store the moving object model in the mixed traffic environment and provide a hierarchical index of the model, wherein the moving object includes vehicle subjects of different intelligence levels; The dynamic element model matching and extraction module is used to receive dynamic object information and scene information collected by the connected vehicle and the intelligent roadside, draw a dynamic object simulation model, match the vehicle subject model with the highest similarity to the dynamic object simulation model in the mixed traffic subject model library, generate an optimal scene drawing sequence according to the received scene information, and send the vehicle subject model and the optimal scene drawing sequence to the connected vehicle; The vehicle-road cooperative perception scene rendering and optimization module is used to generate an optimal scene rendering sequence for the main vehicle of the networked vehicle according to the received vehicle main body model and the optimal scene rendering sequence, and send the optimal scene rendering sequence of the main vehicle to other surrounding networked vehicles; The matching and extraction module of the dynamic element model is specifically used to obtain environmental information through intelligent roadside equipment and other networked intelligent vehicles, organically segment and reshape the environmental data, extract typical hierarchical features, and generate an optimal scene drawing sequence; it also obtains dynamic object information through vehicle-mounted and roadside environmental perception units, performs preliminary block data dimensionality reduction, segmentation processing and reconstruction on the dynamic object information, and then extracts the hierarchical features of the dynamic objects in each block, draws a dynamic object simulation model, and uses a feature correlation function to match the motion object model with the highest similarity to the dynamic object simulation model in the mixed traffic subject model library; The scene drawing and optimization module under vehicle-road cooperative perception is specifically used to generate a subject vehicle drawing sequence according to the received vehicle subject model, synchronize the time and credibility of the optimal scene drawing sequence generated by the matching and extraction module of other connected vehicles and dynamic element models received with the subject vehicle drawing sequence generated by itself, perform sequence slicing on the received information, cross-validate and optimize the redundant area drawing sequence, combine and verify the remaining drawing area sequence, use the adaptive scene drawing sequence optimization function to generate the subject vehicle's optimal scene drawing sequence at the current moment, and send the subject vehicle's optimal scene drawing sequence to other connected vehicles on the same planned path through a wireless network; The scene drawing and optimization module under vehicle-road collaborative perception is specifically used to generate the optimal scene drawing sequence of the main vehicle. The length of each slice sequence is determined by the optimal simulation step of the drawing unit. Each initial scene drawing sequence will be determined according to the result of the previous sequence optimization. The optimization index set is composed of drawing time, information redundancy, information credibility, environmental coverage, environmental fit and scene drawing balance. The index weight is dynamically adjusted according to the index importance preference designed under different scene complexities.

2. The system according to claim 1, characterized in that The mixed traffic subject model library construction module and the dynamic element model matching and extraction module are set in the data center, and the scene drawing and optimization module under vehicle-road collaborative perception is set in the connected vehicle.

3. The system according to claim 1, characterized in that The hybrid traffic subject model library construction module is specifically used to classify and store motion object models through multimedia database technology, decompose each motion object into model primitives, and classify and organize the intelligence level, model and purpose of the subject vehicle in combination with the behavioral characteristic logic of different motion objects. The vehicle elements are analyzed through the hierarchical analysis method, and the vehicle is decomposed into several levels of model primitives to form a hierarchical model index that is mutually related and has a subordinate relationship, and a motion object model index table is constructed.

Images