CN116341185A

CN116341185A - High-precision map simulation method and system

Info

Publication number: CN116341185A
Application number: CN202211655877.5A
Authority: CN
Inventors: 孙亚平
Original assignee: Beijing Jingwei Hirain Tech Co Ltd
Current assignee: Beijing Jingwei Hirain Tech Co Ltd
Priority date: 2022-12-22
Filing date: 2022-12-22
Publication date: 2023-06-27

Abstract

The application discloses a high-precision map simulation method and system, wherein the method comprises the following steps: simulating the high-precision map based on the map processing module, and sending the simulated high-precision map to the fusion module and the local scene generation module; the local scene generation module simulates traffic scene information and driving behavior information of a simulated intelligent vehicle in a test case scene in a simulation scene of the high-precision map, and respectively sends the traffic scene information and the driving behavior information to the fusion module and the automatic driving domain controller; the fusion module fuses the traffic scene information and the driving behavior information into a high-precision map, and sends the fused information to the data broadcasting module; the data broadcasting module sends the fused information to an automatic driving domain controller; the automatic driving domain controller performs simulation test based on the fused information so as to improve the accuracy and the high efficiency of the simulation high-precision map construction, and provides powerful guarantee for the verification of the advanced intelligent driving algorithm of the SOA new architecture vehicle type.

Description

High-precision map simulation method and system

Technical Field

The application relates to the technical field of intelligent driving of automobiles, in particular to a high-precision map simulation method and system.

Background

At present, a new architecture and a cloud end of a simulated intelligent vehicle in an advanced simulation scene based on a Service-oriented architecture (Service-Oriented Architecture) are a great trend, and a high-precision map can provide the perception capability of beyond-the-horizon and provide a basis for vehicle decision control, so that the high-precision map is an important support for high-level intelligent driving realization.

At present, how to solve the difficulty of high-precision map simulation in an SOA vehicle type advanced intelligent driving algorithm, an effective solution is provided for simulation verification of an L4 level automatic driving algorithm, and no good solution exists.

Disclosure of Invention

The embodiment of the application aims to provide a high-precision map simulation method and a high-precision map simulation system so as to improve the accuracy and the high efficiency of simulation high-precision map construction, and provide powerful guarantee for high-grade intelligent driving algorithm verification of an SOA new architecture vehicle type.

In a first aspect, the present application provides a high-precision map simulation method, including:

simulating the high-precision map based on the map processing module, and sending the high-precision map after simulation to the fusion module and the local scene generation module;

the local scene generation module simulates traffic scene information and driving behavior information of a simulated intelligent vehicle in a test case scene in a simulation scene of the high-precision map, and sends the traffic scene information and the driving behavior information to the fusion module and the automatic driving domain controller respectively;

The fusion module fuses the traffic scene information and the driving behavior information into the high-precision map so as to display the traffic scene information and the driving behavior information in the high-precision map, and sends the fused information to the data broadcasting module;

the data broadcasting module sends the fused information to the autopilot domain controller;

and the autopilot domain controller performs simulation test based on the fused information.

In some embodiments of the present application, the simulating the high-precision map based on the map processing module includes:

analyzing the obtained real map data based on the map processing module to obtain road network information corresponding to the real map data,

analyzing the road network information, mapping the analyzed road network information into a simulation high-precision map,

in the process of mapping the analyzed road network information to the simulated high-precision map, obtaining simulated map primitives corresponding to the analyzed road network information,

and based on the acquired simulation map primitives and the road network information, completing the simulation of the high-precision map.

In some embodiments of the present application, before the analyzing the obtained real map data to obtain the road network information corresponding to the real map data, the method further includes:

And acquiring real map data from the merchant high-precision map server.

In some embodiments of the present application, in the process of mapping the parsed road network information to the simulated high-precision map, obtaining a simulated map primitive corresponding to the parsed road network information:

in the process of mapping the road network information to the simulated high-precision map, obtaining simulated map primitives corresponding to the parsed road network information from each simulated map primitive library,

the simulation map primitives stored in each simulation map primitive library are obtained based on real scene scanning.

In some embodiments of the present application, the local scene generating module simulates traffic scene information and driving behavior information of the simulated intelligent vehicle in the test case scene in the simulated scene of the high-precision map, including:

obtaining the position information of the simulation intelligent vehicle in the simulation scene in the high-precision map,

downloading a target precise map in a preset range including the position information in the high-precise map,

responding to the operation of constructing the simulated traffic scene in the target high-precision map by a user, obtaining a test case scene,

and responding to the operation of executing the test case scene by the simulated intelligent vehicle in the simulated scene, and obtaining the traffic scene information and the driving behavior information of the simulated intelligent vehicle in the simulated scene in the test case scene.

In some embodiments of the present application, the obtaining the location information of the simulated intelligent vehicle in the simulated scene in the high-precision map includes:

acquiring initial position information of a simulated intelligent vehicle in a simulated scene, which is acquired by a sensor of the simulated intelligent vehicle in the simulated scene,

and inquiring the high-precision map based on the initial position information, and matching the initial position information with the high-precision map to obtain the position information of the simulated intelligent vehicle in the simulated scene in the high-precision map.

In some embodiments of the present application, the parsing the road network information and mapping the parsed road network information to a simulated high-precision map includes:

analyzing the road network information based on ADAIS V3 standard protocol to obtain path type, path length and path attribute,

and mapping the path model, the path length and the path attribute into the simulation high-precision map.

In some embodiments of the present application, the mapping the path model, the path length, and the path attribute into the simulated high-precision map includes:

mapping the path model, the path length and the path attribute into a simulated high-precision map based on the following mapping rules:

Under the condition that the road network information is that the simulated intelligent vehicle in the simulated scene drives away from the high speed and national road, the bifurcation intersection is indicated based on the first mark,

for branch roads other than the main path, the branch road is indicated based on the second identification,

under the condition that the current position of the simulation intelligent vehicle in the simulation scene is not in a high speed or national road, road network construction is not carried out,

in case of a reconstruction of the road network information, indicating that a reconstruction has occurred based on the third identification,

and describing the relative position of the simulation intelligent vehicle in the simulation scene in the current road network information based on the fourth identification.

In some embodiments of the present application, the map processing module and the data dissemination module are deployed at a cloud end.

In a second aspect, embodiments of the present application further provide a high-precision map simulation system, where the system includes:

the map processing module is used for simulating the high-precision map and sending the simulated high-precision map to the fusion module and the local scene generation module;

the local scene generation module is used for simulating traffic scene information and driving behavior information of running of the simulated intelligent vehicle in a test case scene in a simulation scene of the high-precision map, and respectively sending the traffic scene information and the driving behavior information to the fusion module and the automatic driving domain controller;

The fusion module is used for fusing the traffic scene information and the driving behavior information into the high-precision map, displaying the traffic scene information and the driving behavior information in the high-precision map, and sending the fused information to the data broadcasting module;

the data broadcasting module is used for sending the fused information to the automatic driving domain controller;

and the automatic driving domain controller is used for performing simulation test based on the fused information.

In a third aspect, an embodiment of the present application provides an electronic device, where the electronic device includes a processor, a memory, and a program or instructions stored on the memory and capable of running on the processor, where the program or instructions, when executed by the processor, implement the steps of the high-precision map simulation method according to any one of the embodiments of the present application.

In a fourth aspect, embodiments of the present application provide a readable storage medium having stored thereon a program or instructions that when executed by a processor implement the steps of the high-precision map simulation method described in any of the embodiments of the present application.

In a fifth aspect, embodiments of the present application provide a computer program product, the instructions in which, when executed by a processor of an electronic device, enable the electronic device to perform the steps of the high-precision map simulation method according to any one of the embodiments of the present application.

The technical scheme provided by the embodiment of the application at least brings the following beneficial effects:

in this embodiment of the application, through carrying out the emulation to the high-precision map based on map processing module, so need not the people and set up the high-precision map, saved the human cost, and promoted the precision and the efficiency of constructing of high-precision map. In addition, traffic scene information and driving behavior information are integrated and added into the simulated high-precision map generated after mapping to serve as broadcast data sources, so that the simulated high-precision map traffic scene environment perceived by a simulation sensor in scene simulation software is completely consistent with Ethernet broadcast data received by a high-grade intelligent driving controller, the difficulty of high-precision map simulation in a high-grade intelligent driving algorithm based on an SOA (service oriented architecture) model is solved, a solution is provided for simulation verification of an L4-grade automatic driving algorithm, the cloud traffic scene information and the driving behavior information are recombined and returned, meanwhile, the characteristic of rapid updating and iteration of the SOA model software can be adapted, the time of product development and testing is effectively shortened, and powerful guarantee is provided for high-grade intelligent driving algorithm verification of the SOA model.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application and do not constitute an undue limitation on the application.

Figure 1 is a schematic diagram of a high-precision map simulation system according to an embodiment of the second aspect of the present application,

FIG. 2 is a second schematic diagram of a high-precision map simulation system according to the second embodiment of the present application,

figure 3 is a schematic workflow diagram of a data dissemination module in an embodiment of the present application,

figure 4 is a flow chart of a high-precision map simulation method provided in an embodiment of the first aspect of the present application,

fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of a third aspect of the present application.

Detailed Description

In order to enable those skilled in the art to better understand the technical solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are intended to be illustrative of the application and are not intended to be limiting. It will be apparent to one skilled in the art that the present application may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the present application by showing examples of the present application.

It should be noted that the terms "first," "second," and the like in the description and claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that embodiments of the present application described herein may be implemented in sequences other than those illustrated or otherwise described herein. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present application. Rather, they are merely examples consistent with some aspects of the present application as detailed in the accompanying claims.

In the prior art, when a simulation high-precision map is built at present, a user is required to manually build a simulation high-precision map which is identical to a map box in simulation scene software, and as the high-precision map which is manually built in the simulation software and a real high-precision map in the map box have certain differences, the environment data acquired by an advanced intelligent driving controller according to the high-precision map box are inconsistent with the environment data acquired by a simulation sensor (such as a laser radar camera) in the simulation scene, so that a test result has a problem and cannot be applied, and meanwhile, the manual building is time-consuming and labor-consuming, so that the progress is difficult to ensure.

As described in the background art, in the prior art, when the high-precision map is manually constructed, the efficiency and the accuracy are low, and the traffic scene environment of the high-precision map sensed by the simulation sensor in the scene simulation software is inconsistent with the ethernet broadcast data received by the advanced intelligent driving controller. In addition, traffic scene information and driving behavior information are integrated and added into the simulated high-precision map generated after mapping to serve as broadcast data sources, so that the simulated high-precision map traffic scene environment perceived by a simulation sensor in scene simulation software is completely consistent with Ethernet broadcast data received by a high-grade intelligent driving controller, the difficulty of high-precision map simulation in a high-grade intelligent driving algorithm based on an SOA (service oriented architecture) model is solved, a solution is provided for simulation verification of an L4-grade automatic driving algorithm, the cloud traffic scene information and the driving behavior information are recombined and returned, meanwhile, the characteristic of rapid updating and iteration of the SOA model software can be adapted, the time of product development and testing is effectively shortened, and powerful guarantee is provided for high-grade intelligent driving algorithm verification of the SOA model. The high-precision map simulation method provided by the embodiment of the application is described in detail below through specific embodiments and application scenes thereof with reference to the accompanying drawings.

Before introducing the high-precision map simulation method provided by the embodiment of the application, a high-precision map simulation system for implementing the high-precision map simulation method provided by the embodiment of the application is first introduced.

Fig. 1 is a schematic structural diagram of a high-precision map simulation system provided in an embodiment of the present application, and as shown in fig. 1, the high-precision map simulation system 100 provided in an embodiment of the present application may include a map processing module 110, a local scene generating module 120, a fusion module 130, a data broadcasting module 140, and an autopilot controller 150.

The map processing module 110 is configured to simulate the high-precision map, and send the simulated high-precision map to the local scene generating module 120 and the fusion module 130;

the local scene generating module 120 is configured to simulate, in a simulation scene of the high-precision map, traffic scene information and driving behavior information of the simulated intelligent vehicle in the test case scene, and send the traffic scene information and the driving behavior information to the fusion module 130 and the autopilot domain controller 150, respectively;

the fusion module 130 is configured to fuse the traffic scene information and the driving behavior information into a high-precision map, so as to display the traffic scene information and the driving behavior information in the high-precision map, and send the fused information to the data broadcasting module 140;

The data broadcasting module 140 is configured to send the fused information to the autopilot domain controller 150;

the autopilot domain controller 150 is configured to perform a simulation test based on the fused information.

The test case scene can be a test case of a constructed traffic scene.

The driving behavior information may be driving information of the simulated intelligent vehicle in the simulated scene when the simulated intelligent vehicle runs in the test case scene, specifically, event information such as sudden acceleration, sudden deceleration, sudden turning, overlong idle time, cold start of not-warmed vehicle, neutral sliding, sudden turning and the like, traffic jam information, the type of the simulated intelligent vehicle in the simulated scene (such as a truck/car/motorcycle and the like), and state information (such as speed, position, direction angle, pedestrian speed position and the like) of the simulated intelligent vehicle in the simulated scene.

The map processing module 110, the local scene generating module 120, the fusion module 130, the data dissemination module 140, and the autopilot controller 150 are described in detail below:

(1) Map processing module 110

Referring to fig. 2, the map processing module 110 may specifically include: a high-definition map acquisition and analysis unit 111, a simulated map construction primitive library acquisition unit 112, and a map mapping processing algorithm unit 113.

In some embodiments of the present application, the cloud map processing module 110 is an enterprise private cloud server, a core cloud simulation algorithm is deployed, and depending on a software and hardware platform of the enterprise private cloud system, the cloud server hardware platform may use an 8-core 16G cloud server, an 80G high Input Output (IO) system disk as a hardware bearer, and the whole private cloud software platform may be divided into a scheduling layer, a high performance computing layer and a storage cluster to operate the high-precision map acquisition analysis unit 111, the simulated map building primitive library acquisition unit 112 and the map mapping processing algorithm unit 113.

The following details are provided for the cloud map processing module 110:

(a) High-precision map acquisition and analysis unit 111

The high-precision map acquisition and analysis module 111 can deploy network authorization service of the map manufacturer, update and analyze the latest high-precision map data of the map manufacturer, receive and analyze the road network information, and transmit the road network information to the map mapping processing algorithm module 113.

The map updating service can be deployed on a private cloud server to simulate a real vehicle real map BOX to link a private cloud by means of a 4G network of the T-BOX, and real map data is downloaded through the private cloud network.

The high-precision map obtaining and analyzing unit 111 may be operated in the cloud map processing module 110, and is responsible for remote upgrade (Over-the-Air, OTA) service of the latest high-precision map data of the map vendor, software upgrade package management and operation for implementing OTA upgrade, license management, analyzing the real high-precision map data of the map vendor, and the like, and accessing the internet to obtain the high-precision map data of the map vendor in real time.

(b) Simulation map primitive library acquisition unit 112

The simulated map primitive library obtaining unit 112 is a simulated map primitive library scheduled during running, deployed in local graphic workstations of a plurality of linux systems, each graphic workstation is provided with scene simulation software, reserves a simulated scene primitive library and is provided with a 4G network card, and the graphic workstations are connected with a private cloud server through an access point (Access Point Name, APN) private line.

The simulated map primitive library obtaining unit 112, the transport layer security protocol accesses the local storage cluster, provides services in a dynamic library manner, can interact with the enterprise private cloud server main program, deploys a simulated scene primitive calling algorithm, and the called simulated map primitives include but are not limited to information including lanes, green plants, gradients, speed limits, traffic signboards, traffic marking lines and the like, which are all corresponding to entity three-dimensional model libraries constructed in primitive libraries of a plurality of local map workstations, so that the physical entity with complete real high-precision map information is presented in a simulated software scene in a real centralized manner.

(c) Map processing algorithm unit 113

The map mapping processing algorithm unit 113 is used for mapping the real high-precision map data of the graphics processor to the Opendrive simulation high-precision map, and in the mapping construction process, the simulation map primitive library obtaining unit 112 is used for calling the simulation map primitive libraries of the plurality of local graphic workstations to obtain simulation map primitives, and then the map mapping processing algorithm unit 13 is used for completing the construction of the simulation Opendrive high-precision map, namely the construction of a simulation road network, and the xodr file is automatically generated after the construction work is finished and can be directly downloaded for use by the scene generating module.

In some embodiments of the present application, the map mapping processing algorithm unit 113 may convert the elements of the map operator real high-precision map into the high-precision map in the simulation scene software, and build a high-precision mirror image from the map operator real high-precision map to the simulation high-precision map, and add an optimization algorithm to obtain necessary elements required for the related algorithm of the Service-oriented architecture (Service-Oriented Architecture, SOA) new architecture vehicle type advanced intelligent driving controller.

In some embodiments of the present application, after positioning is completed, the map mapping processing algorithm unit 113 main program may call the intelligent horizon setting GPS coordinate interface function to send a position message to the callback function. The send STUB message indicates the start of the main path and an invalid position message is sent when positioning is not completed.

In some embodiments of the present application, in the mapping process, mapping between the real high-precision map data of the map vendor and the Opendrive simulated high-precision map data may fail, where the cause of the failure may be: the attributes are missing or unavailable during the mapping process.

Data for which attributes are not available may include, but are not limited to, primarily: guardrail properties, road boundary expression mode, isolation belt, curvature description mode, traffic lights, zebra stripes, road reference lines and the like.

The data for which the attributes are missing may include, but is not limited to: lane number change, road type change, or road crossing. At this time, the road is broken and mapped to have a unique ID.

The complete information obtained after the problems are solved can provide a front road network topology for an automatic driving domain controller, and the situation that the distance from the front vehicle is wrongly judged at the curve is prevented. Highway exit information may also be provided to prevent acceleration of the vehicle near the intersection. The vehicle can also provide information such as weather, road surface properties and the like, and the vehicle is guaranteed to slow down.

After the extracted elements are finished, mapping to a simulation map primitive library for feature matching, and the simulation map primitive library acquisition unit 112 accesses a plurality of local primitive libraries which are connected with the network to acquire simulation map primitive data, and simultaneously, performs data reconstruction to realize the construction of a simulation high-precision map road network.

However, only the mapping from the actual high-precision map data of the map maker to the simulated high-precision map data is completed, which is insufficient for the advanced intelligent driving algorithm of the SOA vehicle model with the new architecture, so the embodiment of the application further provides the high-precision map+traffic scene integration module (i.e. the fusion module 130 in fig. 1) so as to be suitable for the advanced intelligent driving system of the SOA vehicle model with the new architecture.

(2) Local scene generation module 120

In some embodiments of the present application, the local scene generation module 120 may provide GPS coordinates (i.e., initial position information) of the simulated intelligent vehicle in the input simulated scene based on the virtual drive test (VIRES Virtual Test Drive, VTD) scene simulation software deployed by the local station, and the map mapping processing algorithm unit 113 receives the GPS information and constructs simulated high-precision map primitives within 10 km based on the position of the real high-precision map based on the coordinates.

The local scene generation module 120 can realize the steps of downloading a high-precision map, constructing a test case scene and acquiring driving behavior information, the simulated intelligent vehicle in the simulated scene is tested and deployed in the local graphical workstation in the simulated high-precision map scene, the graphical workstation runs scene simulation software, a tester can conveniently download the simulated map mapped in the open drive mode through an APN private line, based on the simulated high-precision map, a local simulation scene library is continuously enriched in a mode of constructing a self-defined simulated scene, and then the simulated high-precision map is connected and returned to a cloud server, the map downloading range can be the round data with the position coordinate radius of 10 km in the simulated intelligent vehicle in the simulated scene, the positioning mode is that after the simulation software runs, the simulated vehicle acquires initial position information based on a sensor, inquires by using a feature landmark, inquires about the feature landmark of the high-precision map based on the initial position information, and acquires the simulated position of the simulated intelligent vehicle based on the high-precision map layer information and real-time perceived simulation feature information (such as radar point cloud, camera video image information and the like). At this time, no traffic scene information is needed to be manually built in scene simulation software according to the design of the test case, the traffic scene information such as the actions and the quantity of people and vehicles is added, and after the completion and the storage, the traffic scene information (namely the test case scene) is returned to a fusion module of a cloud server, the traffic scene information and the simulated high-precision map information are integrated to form a simulated high-precision map and scene data, and the simulated high-precision map and scene data are transmitted to a data broadcasting module to realize a data broadcasting module 140, and are broadcasted to an autopilot controller 150 on the Ethernet through an ADSIS V3 protocol, so that the high-precision map in the simulated scene is completely consistent with the high-precision map information received by the autopilot controller 150, the road network topology which can be driven by the simulated vehicle is detected based on the autopilot is realized, the vision of the vehicle is widened, the obtained high-precision map data are transmitted to the simulated vehicle end, the traffic conditions such as congestion and the optimal autopilot route is realized, and the front road shape and the data information beyond vision are provided for advanced intelligent driving application.

(3) Fusion module 130

The fusion module 130 runs in the enterprise private cloud server together with the map processing module 110, and is responsible for adding the returned traffic scene information (i.e. the test case scene) and the driving behavior information into the simulated high-precision map generated after mapping, and transmitting the traffic scene information and the driving behavior information to the data broadcasting module 140.

After the map mapping processing algorithm unit 113 completes the accurate mapping from the map operator high-precision map data to the simulated high-precision map data, based on the scene simulation software VTD deployed by the local scene generating module 120, traffic scene information and driving behavior information are added on the basis of the downloaded primary mapping Opendrive virtual map, and the traffic scene information and driving behavior information are transmitted back to the fusion module 130 and transmitted to the data broadcasting module 140 together through an expansion protocol, specifically, the information such as GPS position information, traffic scene, driving state and the like can be transmitted back through the local scene generating module 120. The data backhaul and the scene data backhaul may be implemented by receiving traffic scene information manually built in scene simulation software in an extension protocol, screening and obtaining relevant element features required by the autopilot domain controller 150, then sending ethernet information to a callback function interface, and registering a callback function by the interface to implement a main program, where the main function of the callback function is to receive content transmitted by an extension protocol part: and adding traffic information, driving state and other information into the cloud processing based on the content which is supplemented by the reserved bit of the ADAIS V3 protocol. After that, the callback function receives the message sent by the local scene generating module 120 every time the GPS coordinate interface is called, and completes the functions of vehicle positioning, road network information and road gradient information compiling and outputting, so that the high-level optimal path (most probable path, MPP) maximum likelihood path identifying function is realized, the path of the vehicle owner most likely to drive can be identified based on the constructed road network topological relation, navigation, cruising and other states, and an optimal solution is provided for optimal route planning of the autopilot domain controller 150.

(4) Data broadcasting module 140

Referring to fig. 3, the data dissemination module 140 may implement: the steps of high-precision map+traffic scene ADSIS V3 protocol analysis and high-precision map+traffic scene ADSIS V3 protocol broadcasting aim to broadcast high-precision map data in a specified kilometer after vehicle positioning so that the automatic driving domain controller 150 can complete map data reconstruction.

The data broadcasting module 140 organizes and transmits the information of the reconstructed simulation high-precision map, and completes the information broadcasting of the high-precision map and the reconstructed traffic scene integrating module through the vehicle-mounted ethernet bus transmission, and provides the functions of the road network (namely traffic information), message packaging, message transmission and the like in front of the simulation intelligent vehicle position based on the simulation scene for the autopilot domain controller 150 in advance.

The data broadcasting module 140 broadcasts data such as traffic scene data and driving behavior of the simulated intelligent vehicle in the simulated scene through the expansion protocol in addition to the high-precision map data of the adis V3 protocol. The specific form is as follows: message organization and sending, namely, based on road network construction results, the attribute information on the road network is organized into messages defined in standard ADAISIS v3, and the messages are sent to a vehicle Ethernet bus, and the broadcasted data structure is integrated data of two parts of data, mainly including but not limited to: part of the ADAIS society transmits a defined standard V3 information transmission protocol to the Ethernet bus aiming at a map, and the standard vehicle front road geometry and attribute information obtained according to the position information and the map data of the vehicle are realized, so that the vehicle front road geometry and attribute information meet the vehicle rule level requirements. The other part is to receive the data feedback and scene data feedback of the information such as GPS position information, driving state and the like, receive the traffic scene information manually built in a scene editor of scene simulation software of a tester in an expansion protocol, screen and acquire relevant element characteristics required by the autopilot controller 150, send the relevant element characteristics to the autopilot controller 150 at the simulation vehicle end, and then analyze and execute the relevant element characteristics to realize the application of the advanced intelligent driving function.

The implementation manner of the standard V3 information transmission protocol defined by the transmission to the ethernet bus may specifically be to analyze and broadcast the broadcasted scene element of the simulated high-precision map in the specified kilometer, including but not limited to intersections, lane lines, line near-end geometric parameters, line far-end geometric parameters, traffic signs, traffic lights, road types (Profile types), traffic scene information, driving behavior information of the simulated intelligent vehicle in the simulated scene, and other information.

(5) Autopilot controller 150

The autopilot domain controller 150 includes an autopilot algorithm requiring a verification test, and includes interfaces such as a controller area network (Controller Area Network, CAN), ethernet, IO, LVDS, and the like.

According to the high-precision map simulation system, by means of the advantages of cloud simulation, main high-precision map mapping, scheduling, reorganizing and broadcasting algorithms are operated on the cloud, scene libraries in a plurality of networking local map stations are allocated, infinite expansion of map primitives and scene primitives is achieved, the mapping algorithm deployed on the cloud can accurately obtain simulation scene primitives with higher matching degree with real high-precision map data primitives of a map operator, further, the simulation high-precision map generated by mapping can accurately restore the real high-precision map, meanwhile, traffic scene data and driving behavior data are integrated and added into the simulation high-precision map generated after mapping to serve as data sources for broadcasting, data broadcasting on an Ethernet is completed in a specified kilometer after vehicle positioning, the simulation high-precision map traffic scene environment perceived by a simulation sensor in scene simulation software is achieved, the simulation scene primitives are completely consistent with Ethernet broadcasting data received by a high-grade intelligent driving controller, the difficulty of high-precision map simulation in the high-grade intelligent driving algorithm is solved, and a simulation verification scheme for the L4-grade automatic driving algorithm is provided.

Referring to the following details of the high-precision map simulation method provided in the embodiment of the present application, as shown in fig. 4, the high-precision map simulation method provided in the embodiment of the present application may include steps 410 to 450:

step 410, the high-precision map is simulated based on the map processing module, and the simulated high-precision map is sent to the fusion module and the local scene generation module.

Step 420, the local scene generating module simulates traffic scene information and driving behavior information of the simulated intelligent vehicle in the test case scene in the simulation scene of the high-precision map, and sends the traffic scene information and the driving behavior information to the fusion module and the automatic driving domain controller respectively.

And 430, the fusion module fuses the traffic scene information and the driving behavior information into the high-precision map so as to display the traffic scene information and the driving behavior information in the high-precision map, and sends the fused information to the data broadcasting module.

Step 440, the data broadcasting module sends the fused information to the autopilot domain controller.

And 450, performing simulation test by the autopilot domain controller based on the fused information.

In the embodiment of the application, the high-precision map is simulated based on the map processing module, so that the high-precision map does not need to be manually built, the labor cost is saved, and the precision and the construction efficiency of the high-precision map are improved. In addition, traffic scene information and driving behavior information are integrated and added into the simulated high-precision map generated after mapping to serve as broadcast data sources, so that the simulated high-precision map traffic scene environment perceived by a simulation sensor in scene simulation software is completely consistent with Ethernet broadcast data received by a high-grade intelligent driving controller, the difficulty of high-precision map simulation in a high-grade intelligent driving algorithm based on an SOA (service oriented architecture) model is solved, a solution is provided for simulation verification of an L4-grade automatic driving algorithm, the cloud traffic scene information and the driving behavior information are recombined and returned, meanwhile, the characteristic of rapid updating and iteration of the SOA model software can be adapted, the time of product development and testing is effectively shortened, and powerful guarantee is provided for high-grade intelligent driving algorithm verification of the SOA model.

In some embodiments of the present application, to further improve the accuracy and efficiency of the accurate map simulation, step 210 may specifically include:

and based on the acquired simulation map primitives and road network information, completing the simulation of the high-precision map.

Wherein the real map data may be real map information of a place.

The road network information may be a case of a road network corresponding to the real map data.

In some embodiments of the present application, the implementation of the above steps is implemented in the map processing module 110 in fig. 1, specifically may be that the high-precision map obtaining and analyzing unit 111 is configured to analyze the obtained real map data to obtain road network information corresponding to the real map data, and send the road network information to the map mapping processing algorithm unit 113, where the map mapping processing algorithm unit 113 is configured to analyze the obtained road network information, and map the analyzed road network information to the simulated high-precision area

In the figure, the simulated map building primitive library obtaining unit 112 is configured to obtain simulated map primitives corresponding to the road network information after analysis by the map mapping processing algorithm unit 113 in a process of mapping the road network 5 information after analysis to the simulated high-precision map, and map the simulated map primitives

The emission processing algorithm unit 113 is configured to complete the simulation of the high-precision map based on the acquired simulation map primitive and the road network information.

In some embodiments of the present application, the map processing module 110 may be deployed in the cloud, so by virtue of various advantages of cloud simulation, the scheme of deploying the high-precision map core processing algorithm in the cloud simulation is adopted, which becomes a powerful way for breaking through the difficulty of solving the problem

The accurate mapping and the rapid generation of the real high-precision map mapping Opendrive simulation high-precision map are realized by utilizing cloud computing capability by means of the high-efficiency, collaborative, visual, data security and other layers of high-precision map cloud simulation.

In the embodiment of the application, the road network information corresponding to the real map data is obtained by analyzing the acquired real map data based on the map processing module, the road network information is analyzed, the analyzed road network information is mapped into the simulated high-precision map, and in the process of mapping the analyzed road network information into the simulated high-precision map, the road network information pair after analysis is acquired

And 5, the simulation of the high-precision map is completed based on the acquired simulation map elements and road network information, so that the simulation of the high-precision map can be accurately and rapidly completed.

In some embodiments of the present application, the parsing the road network information and mapping the parsed road network information to the simulated high-precision map may specifically include:

and analyzing the road network information based on the ADAIS V3 standard protocol to obtain the path type, the path length and the path attribute, and mapping the path model, the path length and the path attribute into the simulation high-precision map.

0 in some embodiments of the present application, when parsing road network information, ADAIS V3 standard protocol may be employed

The method includes the steps of obtaining analyzed road network information from international standard ((Advanced Driver Assistant System Interface Specification) which is a standard interface protocol for standardizing navigation map data and vehicle-side transmission), obtaining a path type, a path length and a path attribute, and mapping the path model, the path length and the path attribute into a simulated high-precision map.

In some embodiments of the present application, the parsed road network information may specifically further include a type, where the type may include 5Position, profileShort, stub, segment, profile Long, meta_data, and specifically includes information such as gradient, curvature, number of lanes, lane line type, line geometry, landmark, road boundary, and the like.

In some embodiments of the present application, a Position message may be used to describe the Position of a vehicle in a map. Profile Short may describe gradient information of a road. The Opendrive simulation high-precision map of the mapping object mainly comprises three characteristics of a road reference line (reference line), a lane (Lanes) and a road facility (Features), wherein elements mainly comprise a road center line, a course description, a road height fluctuation, a road cross slope, a lane connection relationship, a road type definition mode, a lane widening and shunting description, a lane narrowing and converging description, a tunnel object expression mode, a road curve description, a signal lamp expression and the like.

In some embodiments of the present application, the simulated map primitive may be a map primitive corresponding to the parsed road network information, and the simulated map primitive may specifically include, but is not limited to: lane, green plants, gradient, speed limit, traffic sign, traffic marking, etc.

In the embodiment of the application, the road network information is analyzed based on the ADAIS V3 standard protocol to obtain the path type, the path length and the path attribute, and then the path model, the path length and the path attribute can be mapped into the simulation high-precision map, so that the high-precision map with the accurate path model, the path length and the path attribute can be obtained, and the simulation precision of the follow-up intelligent driving vehicle is improved.

the path type, path length and path attributes are mapped into a simulated high-precision map based on the following rules:

in case of a reconstruction of the road network information, the reconstruction is indicated to occur based on the third identification,

and describing the relative position of the simulated intelligent vehicle in the simulated scene in the current road network information based on the fourth identifier.

The first identifier may be a preset identifier for indicating a bifurcation intersection, and specifically may be a special STUB in an ADAIS V3 standard protocol.

The second identifier may be an identifier for characterizing a branch road, so as to ensure that the topology road network type of the main path 2000m in front of the simulated intelligent vehicle in the simulated scene is high-speed or national road.

The third identifier may be used to characterize the occurrence of the reconstruction.

The fourth identification may be used to describe the relative position of the simulated intelligent vehicle in the simulated scene in the current road network information.

In some embodiments of the present application, when mapping the path type, the path length and the path attribute into the simulated high-precision map, the road network ahead may be constructed according to the scene sending gradient data, the curvature data, the intersection data and the current position of the vehicle, so that the accurate simulated high-precision map may be obtained.

In the embodiment of the application, the path type, the path length and the path attribute are mapped into the simulation high-precision map through specific rules, so that the accuracy and consistency of the obtained simulation high-precision map can be ensured.

In the prior art, a high-precision map is simulated, in local graphic workstation scene simulation software, a limited software self-contained primitive is used, an Opendrive format simulation high-precision map is manually built, then, on one hand, the manually built Opendrive format simulation high-precision map is converted into a real high-precision map box identifiable format, the real map box is used for being broadcast to an automatic driving controller, on the other hand, the manually built Opendrive format simulation high-precision map is imported into local scene simulation software, so that a simulation vehicle can sense through a simulation sensor, and the mode can ensure that data broadcast by the map box are consistent with simulation environment data sensed by the simulation vehicle.

However, the above solution is difficult to be universally implemented due to the difficulty of converting the Opendrive format into the map data available in the map box of the map manufacturer and the customization problem of different map manufacturers, and the conversion solution needs to be customized and developed with specific map manufacturers, so that the workload and the cost of developing the conversion are increased geometrically along with the increase of the number of the maps, and the cost is huge, the efficiency is low, and the universal implementation is not facilitated.

In order to solve the above-mentioned problems and further improve accuracy of the simulation of the high-precision map, in some embodiments of the present application, before analyzing the obtained real map data to obtain the road network information corresponding to the real map data, the above-mentioned high-precision map simulation method may further include:

the real map data is obtained from the merchant high-precision map server,

and analyzing the real map data to obtain road network information corresponding to the real map data.

In some embodiments of the present application, the above steps may be implemented based on the high-precision map acquisition and analysis unit 111, where the high-precision map acquisition and analysis unit 111 may be in communication connection with a merchant high-precision map server, from which real map data is acquired.

In the embodiment of the application, the real map data are acquired from the merchant high-precision map server, so that the real map data are acquired from the merchant, the last simulated high-precision map is ensured to correspond to the requirements of the merchant, the customization requirements of the merchant are met, and meanwhile, the acquired real map data are the real map data acquired from the merchant, so that the accuracy of the simulated high-precision map is further ensured.

In some embodiments of the present application, in order to further improve accuracy of the simulated high-precision map, in some embodiments of the present application, in a process of mapping the parsed road network information to the simulated high-precision map, obtaining a simulated map primitive corresponding to the parsed road network information may specifically include:

in the process of mapping the road network information to the simulated high-precision map, the simulated map primitives corresponding to the parsed road network information are acquired from each simulated map primitive library.

Wherein, the simulation map primitives stored in each simulation map primitive library can be obtained based on real scene scanning.

In some embodiments of the present application, the above steps may be implemented based on the simulated map building primitive library obtaining unit 112, where the simulated map building primitive library obtaining unit 112 may be communicatively connected to at least one simulated map primitive library of the local graphics workstation, and obtain the simulated map primitive corresponding to the parsed road network information from the at least one simulated map primitive library.

In the embodiment of the application, because the simulation map primitives stored in the simulation map primitive library can be obtained based on real scene scanning, the obtained simulation map primitives are very close to the real scene, and the high-precision map constructed in this way is also close to the real scene, so that the accuracy of the simulation high-precision map is further ensured. The map processing module is deployed at the cloud, and the main high-precision map mapping and scheduling algorithm is operated at the cloud by virtue of the advantages of cloud simulation, so that scene libraries in a plurality of networking local map stations are allocated, infinite expansion of map primitives and scene primitives is realized, the mapping algorithm deployed at the cloud is ensured to accurately obtain simulation scene primitives with higher matching degree with real high-precision map data primitives of a map operator, and further, the simulated high-precision map generated by mapping can be ensured to accurately restore the real high-precision map.

In some embodiments of the present application, to ensure the safety of the simulated intelligent vehicle in the simulated scenario, step 420 may specifically include:

obtaining the position information of the simulated intelligent vehicle in the simulated scene in the high-precision map,

Responding to the operation of constructing the simulated traffic scene in the target precise map by the user, obtaining a test case scene,

and responding to the operation of executing the test case scene by the simulated intelligent vehicle in the simulation scene, and obtaining driving behavior information of the simulated intelligent vehicle in the simulation scene in the test case scene.

The preset range may be a preset range including position information, for example, a range within 10 km including position information may be a preset range. The preset range can be set according to the user's requirement, and is not limited herein.

The target precision map may be a high precision map within a preset range including the position information.

In the embodiment of the application, the simulation intelligent vehicle in the simulation scene executes the test case scene according to the simulation traffic scene built in the target high-precision map, so that driving behavior information can be obtained, different simulation traffic scenes and driving behavior information of the simulation intelligent vehicle in the simulation scene under different simulation traffic scenes can be obtained, the simulation intelligent vehicle in the simulation scene can be ensured to run according to the simulated driving behavior information when encountering the same traffic scene in the subsequent real scene, and the safety of the simulation intelligent vehicle in the simulation scene is ensured.

In some embodiments of the present application, in order to accurately obtain the position information of the simulated intelligent vehicle in the simulated scene in the high-precision map, the obtaining the position information of the simulated intelligent vehicle in the simulated scene in the high-precision map may specifically include:

acquiring initial position information of the simulated intelligent vehicle in the simulated scene acquired by the sensor of the simulated intelligent vehicle in the simulated scene,

The initial position information may be position information of the simulated intelligent vehicle in a simulated scene acquired by a sensor of the simulated intelligent vehicle in the simulated scene.

In some embodiments of the present application, the sensors may be a global positioning system (Global Positioning System, GPS), an inertial measurement unit (inertial measurement unit, IMU), a vehicle speed sensor, and a steering wheel angle sensor.

In the embodiment of the application, the high-precision map is queried based on the initial position information of the simulated intelligent vehicle in the acquired simulated scene, which is acquired by the sensor of the simulated intelligent vehicle in the simulated scene, and the position information of the simulated intelligent vehicle in the simulated scene in the high-precision map can be accurately obtained by matching the initial position information with the high-precision map.

In some embodiments of the present application, by the high-precision map simulation system, a high-precision map simulation method for simulating an intelligent vehicle in a simulation scene as follows may be implemented:

step S1, a high-precision map acquisition and analysis unit performs map update initialization, acquires permission verification information, computing resource information, breakpoint reduction, judges whether the breakpoint and breakpoint recovery of non-switched data, unreduced data and unreduced data exist, downloads and verifies a map data update package, copies a high-precision map which is being used in a map area to an update area in a data analysis process, and performs restoration and verification of the update package on the basis to generate a new version of high-precision map.

Step S2, the map processing module receives GPS original information transmitted by the local scene generating module through the APN, the fusion module acquires vehicle positioning information, the high-precision map acquisition and analysis unit finishes positioning of the vehicle on the map by utilizing the analyzed GPS information, and transmits a positioning result to the map mapping processing algorithm unit to inquire real high-precision map data after analysis in a formulated kilometer, construct a road network, establish topology, construct a message and cache, and calculate own vehicle positions (Current Car Position, CCP) and construct an environment map.

And S3, the data broadcasting module acquires simulated high-precision map data integrated by the fusion module in a certain kilometer in a coordinate system, and transmits the simulated high-precision map data to the automatic driving domain controller through the vehicle-mounted Ethernet, meanwhile, a simulated vehicle runs in the scene generating module, and a simulated sensor of the simulated vehicle simultaneously senses a simulated high-precision map scene of traffic scene software VTD in the scene generating module, so that the cloud simulation application of the high-precision map is realized.

Based on the same inventive concept, the embodiment of the application also provides electronic equipment.

Fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application. As shown in fig. 5, the electronic device may include a processor 501 and a memory 502 storing computer programs or instructions.

In particular, the processor 501 may include a Central Processing Unit (CPU), or an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), or may be configured as one or more integrated circuits that implement embodiments of the present invention.

Memory 502 may include mass storage for data or instructions. By way of example, and not limitation, memory 502 may comprise a Hard Disk Drive (HDD), floppy Disk Drive, flash memory, optical Disk, magneto-optical Disk, magnetic tape, or universal serial bus (Universal Serial Bus, USB) Drive, or a combination of two or more of the foregoing. Memory 502 may include removable or non-removable (or fixed) media, where appropriate. Memory 502 may be internal or external to the integrated gateway disaster recovery device, where appropriate. In a particular embodiment, the memory 502 is a non-volatile solid state memory. The Memory may include read-only Memory (Read Only Memory image, ROM), random-Access Memory (RAM), magnetic disk storage media devices, optical storage media devices, flash Memory devices, electrical, optical, or other physical/tangible Memory storage devices. Thus, in general, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software comprising computer-executable instructions and when the software is executed (e.g., by one or more processors) it is operable to perform the operations described by the high-precision map simulation method provided by the above embodiments.

The processor 501 implements any one of the high-precision map simulation methods of the above embodiments by reading and executing the computer program instructions stored in the memory 502.

In one example, the electronic device may also include a communication interface 503 and a bus 510. As shown in fig. 5, the processor 501, the memory 502, and the communication interface 503 are connected to each other by a bus 510 and perform communication with each other.

The communication interface 503 is mainly used to implement communication between each module, device, unit and/or device in the embodiments of the present invention.

Bus 510 includes hardware, software, or both that couple components of the electronic device to one another. By way of example, and not limitation, the buses may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an infiniband interconnect, a Low Pin Count (LPC) bus, a memory bus, a micro channel architecture (MCa) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a video electronics standards association local (VLB) bus, or other suitable bus, or a combination of two or more of the above. Bus 510 may include one or more buses, where appropriate. Although embodiments of the invention have been described and illustrated with respect to a particular bus, the invention contemplates any suitable bus or interconnect.

The electronic device can execute the collision detection method of the intelligent driving vehicle in the embodiment of the invention, thereby realizing the high-precision map simulation method described in fig. 4.

In addition, in combination with the high-precision map simulation method in the above embodiment, the embodiment of the invention can be implemented by providing a readable storage medium. The readable storage medium has stored thereon program instructions which, when executed by a processor, implement any of the high-precision map simulation methods of the above embodiments.

In addition, in combination with the high-precision map simulation method in the above embodiment, the embodiment of the invention can be implemented by providing a computer program product. The instructions in the computer program product, when executed by a processor of an electronic device, enable the electronic device to perform any one of the high-precision map simulation methods of the above embodiments.

It should be understood that the invention is not limited to the particular arrangements and instrumentality described above and shown in the drawings. For the sake of brevity, a detailed description of known methods is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present invention are not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between steps, after appreciating the spirit of the present invention.

The functional blocks shown in the above-described structural block diagrams may be implemented in hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, a plug-in, a function card, or the like. When implemented in software, the elements of the invention are the programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine readable medium or transmitted over transmission media or communication links by a data signal carried in a carrier wave. A "machine-readable medium" may include any medium that can store or transfer information. Examples of machine-readable media include electronic circuitry, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio Frequency (RF) links, and the like. The code segments may be downloaded via computer networks such as the internet, intranets, etc.

It should also be noted that the exemplary embodiments mentioned in this disclosure describe some methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the above-described steps, that is, the steps may be performed in the order mentioned in the embodiments, or may be performed in a different order from the order in the embodiments, or several steps may be performed simultaneously.

Aspects of the present application are described above with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions/acts specified in the flowchart and/or block diagram block or blocks. Such a processor may be, but is not limited to being, a general purpose processor, a special purpose processor, an application specific processor, or a field programmable logic circuit. It will also be understood that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware which performs the specified functions or acts, or combinations of special purpose hardware and computer instructions.

While the invention has been described with reference to a preferred embodiment, it will be apparent to those skilled in the art that the scope of the invention is not limited thereto, and various equivalent modifications and substitutions can be made therein by those skilled in the art without departing from the scope of the invention.

Claims

1. A high-precision map simulation method, characterized in that the method comprises:

2. The method of claim 1, wherein the simulating a high-precision map based on a map processing module comprises:

3. The method according to claim 2, wherein before the analyzing the obtained real map data to obtain the road network information corresponding to the real map data, the method further comprises:

and acquiring real map data from the merchant high-precision map server.

4. The method according to claim 2, wherein in the process of mapping the parsed road network information to the simulated high-precision map, a simulated map primitive corresponding to the parsed road network information is acquired:

5. The method of claim 1, wherein the local scene generation module simulates traffic scene information and driving behavior information of a simulated intelligent vehicle in a test case scene in a simulated scene of the high-precision map, comprising:

6. The method of claim 5, wherein the obtaining location information of the simulated intelligent vehicle in the simulated scene in the high-precision map comprises:

7. The method according to claim 2, wherein the parsing the road network information and mapping the parsed road network information into a simulated high-precision map includes:

8. The method of claim 7, wherein mapping the path model, path length, and path attributes into the simulated high-precision map comprises:

9. The method of claim 1, wherein the map processing module and the data dissemination module are deployed at a cloud.

10. A high-precision map simulation system, the system comprising: