CN113777952A - Automatic driving simulation test method for interactive mapping of real vehicle and virtual vehicle - Google Patents
Automatic driving simulation test method for interactive mapping of real vehicle and virtual vehicle Download PDFInfo
- Publication number
- CN113777952A CN113777952A CN202110952185.6A CN202110952185A CN113777952A CN 113777952 A CN113777952 A CN 113777952A CN 202110952185 A CN202110952185 A CN 202110952185A CN 113777952 A CN113777952 A CN 113777952A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- real
- data
- simulation
- test
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B17/00—Systems involving the use of models or simulators of said systems
- G05B17/02—Systems involving the use of models or simulators of said systems electric
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides an automatic driving simulation test method for interactive mapping of a real vehicle and a virtual vehicle, aiming at the requirement that the automatic driving vehicle needs to be subjected to a large number of tests before actually landing. Firstly, a set of virtual test scenes is set up in simulation software according to real test site mapping data. When the real vehicle travels in the experimental site, the virtual vehicle is simulated in the virtual scene to run simultaneously, and the real scene and the virtual scene are mapped interactively. The test system fuses virtual vehicle data in the virtual scene with real test vehicle data to form a comprehensive data test scene. In the test running process, the virtual vehicle can simulate the action of the real vehicle, the virtual vehicle and the real test vehicle are mutually influenced, and the test process of the real test vehicle is completed through the assistance of the virtual scene and the virtual vehicle.
Description
Technical Field
The invention relates to the field of intelligent transportation, automatic driving, digital twinning and in-loop simulation, in particular to an automatic driving simulation test method for interactive mapping of a real vehicle and a virtual vehicle
Background
With the rapid development of technologies such as artificial intelligence, wireless communication, informatization and the like in recent years, the development of automatic driving is greatly promoted. However, the automatic driving automobile must be subjected to a large number of tests to actually realize the landing. At present, three methods are mainly used for testing an automatic driving vehicle, namely a software virtual test, a hardware-in-loop simulation test and a real road test. The methods have some defects, a large number of mathematical models are required to be constructed in the software virtual test, the mathematical models are complicated to construct and cannot truly reflect the dynamic characteristics of the vehicle, and the hardware-in-loop simulation test is mainly to fix the vehicle in the loop; the acceleration and deceleration process of the vehicle cannot be truly simulated, and the test platform is expensive to manufacture. The real road test needs to build a road test site, and enterprises cannot bear the economic cost and the time cost. Therefore, some economic and effective test methods are urgently needed for the automatic driving technology to finally realize the application.
The Digital Twin (DT) is also translated into Digital Twin, Digital image, or Digital mapping, which is driven by new generation information technology and manufacturing technology, fully utilizes data such as physical model, sensor update, operation history and the like, integrates simulation processes of multidisciplinary, multi-physical quantity, multi-scale and multi-probability, and completes mapping in virtual space, thereby reflecting the whole life cycle process of corresponding entity equipment. The digital twin is used as a digital copy of the physical system, the whole life cycle of the operating system can be simulated, synchronous mapping is carried out on the digital twin and the physical twin, and related data of the physical entity and the digital entity are interacted in real time, so that simulation related applications such as analysis, prediction, decision and the like are supported. The digital twin provides a new idea for the analysis and solution of the traffic problem.
Disclosure of Invention
The invention provides an automatic driving simulation test method for interactive mapping of a real vehicle and a virtual vehicle, which is used for testing an automatic driving vehicle and aims at solving the problems of high cost, long time consumption, low precision, difficulty in repeatedly realizing the same scene and the like of the traditional automatic driving vehicle test method. The method creatively introduces a digital twin technology, and firstly builds a set of virtual test scenes matched with a real scene 1:1 in a simulation environment according to geometric data of a real test site. A wide field can be selected for experiment, when a real vehicle travels in the actual field, a digital twin body of the real vehicle is constructed in simulation software, and the digital twin body runs synchronously. In the test process, the virtual vehicle can simulate the action of the real vehicle and influence the operation of other virtual vehicles in the simulation environment, the virtual vehicle in the simulation environment can also influence the operation state of the real vehicle, the interactive mapping of a real scene and a virtual scene is realized, and the aim of testing the automatic driving vehicle is finally achieved.
In order to realize the automatic driving simulation test method for interactive mapping of the real vehicle and the virtual vehicle, the following technical scheme is adopted:
firstly, selecting an actual test road and obtaining geometric data of the actual test road according to the automatic driving test requirement, and then constructing a set of simulation scenes matched with a real test scene 1:1 in simulation software according to the geometric data. When the automatic driving test is carried out, only one open field is needed to be selected, two points in the open field are selected, the longitude and latitude information of the two points is obtained through a GPS, and then the longitude and latitude information is converted into coordinates in a Gaussian plane coordinate system. Coordinates of two corresponding points in the simulated road network are obtained, and a coordinate conversion relation between the actual coordinates and the simulated coordinates is determined through the following coordinate system conversion formula.
In the formula (x)i,yi) The coordinate position of the ith point in the actual test scene in the Gaussian plane coordinate system is defined, wherein (x, y) is the coordinate position of the coordinate point corresponding to the ith point in the actual test scene in the simulation coordinate system, and (delta x (i), (delta y (i)), alpha (i)) is the position and the rotation angle of the Gaussian plane coordinate system relative to the xoy coordinate system in the simulation scene.
And (2) acquiring the position, speed, acceleration and course angle data of the vehicle through a sensor on the real vehicle, and storing the data into the state member variable of the current vehicle after Kalman filtering. And (3) converting the real vehicle state data according to the coordinate conversion relation established in the step (1) when the vehicle state information is read, and sending the converted real vehicle state data to the database. Meanwhile, the simulation vehicle in the simulation software continuously converts the position, the speed, the acceleration, the course angle, the length, the width and the timestamp data of data acquisition of the vehicle with the coordinate conversion relation established in the step (1) in the running process, and sends the converted data to the database. Therefore, data interaction between the real vehicle and the simulated vehicle is realized.
And (3) continuously reading the position, speed, acceleration, course angle, vehicle length and vehicle width data of the real vehicle from the database by simulation software, and generating a digital twin of the real vehicle on a simulation road network in real time according to the data, wherein the motion state of the digital twin is consistent with the motion state of the real vehicle. In addition, the program on the real vehicle continuously reads the relevant data of the simulated vehicle from the database, stores the data into the state linked list of other vehicles, then carries out conflict judgment according to the information of other vehicles, generates a corresponding resolution strategy, and controls the real vehicle according to the generated resolution strategy. Therefore, the purpose of mutual influence between the virtual vehicle and the real test vehicle is achieved.
And (4) analyzing the position, the speed, the acceleration and the course angle of the real vehicle. And comparing the target position, speed, acceleration and course angle of a control algorithm in the simulation software. And evaluating a control algorithm in the simulation software according to the deviation between the actual data and the target position, speed, acceleration and course angle.
Drawings
FIG. 1 is an overall block diagram of the present invention
FIG. 2 is a schematic diagram of a simulated road network
FIG. 3 is a schematic diagram of a coordinate transformation input interface
FIG. 4 is a diagram of a vehicle _ status list element
FIG. 5 is a diagram of the elements of the car _ status table
FIG. 6 is a schematic diagram of simulation operation
FIG. 7 is a schematic view of an operation interface of an actual vehicle
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings and embodiments. It should be understood that this example is intended to illustrate the invention only and is not intended to limit the scope of the invention. The overall block diagram of the automatic driving simulation test method for interactive mapping of real vehicles and virtual vehicles provided by the invention is shown in fig. 1, and the specific implementation method comprises the following steps:
firstly, according to the test requirement of the automatic driving vehicle, a certain cross-shaped actual road comprising an intersection is selected, and the intersection is a typical four-inlet intersection. Each inlet comprises two inlet lanes and three outlet lanes. According to the measured geometric data of the cross road, a simulation road network matched with 1:1 as shown in fig. 2 is constructed in simulation software TSimitor. When the automatic driving test is performed, an open field is selected, any two points on the open field are selected, the GPS coordinates of the two points are measured, the coordinates of the two points in the simulated road network are obtained, the input is performed on the interface shown in fig. 3, and the determination is performed by clicking. The program converts the automatic GPS coordinates into coordinates in a gaussian plane coordinate system, and determines the coordinate conversion relationship between the actual coordinates and the simulated coordinates through the following coordinate system conversion formula.
And (2) acquiring the position, speed, acceleration and course angle data of the vehicle by a sensor loaded on the vehicle in the advancing process of the real vehicle, and storing the data into the state member variables of the current vehicle after Kalman filtering. Converting the real vehicle state data according to the coordinate conversion relation established in the step (1) when reading the vehicle state information, the data information is transmitted to a table named vehicle _ status in the database, and specifically, the transmitted data information includes vehiid (ID of vehicle), bSimulator (whether it is a real vehicle), time (time stamp), roadID (ID of road), edgeID (ID of edge), laned (ID of lane), positionOnLane (position of vehicle from the start point of lane), positionLat (lateral position of vehicle on lane), x (x coordinate of vehicle in simulation coordinate system), y (y coordinate of vehicle in simulation coordinate system), z (z coordinate of vehicle in simulation coordinate system), yaw (heading angle), vx (component of speed in x-axis direction), vy (component of speed in y-axis direction), ax (component of acceleration in x-axis direction), and acceleration (component of ay in y-axis direction), as shown in fig. 4. Meanwhile, the simulation vehicle in the simulation software TSestimator continuously converts the data related to the virtual vehicle during the operation process, and sends the data to the car _ status table in the database. As shown in fig. 5, the transmitted specific information includes card ID (ID of virtual vehicle), TimeOfStatus (time stamp), card length (length of virtual vehicle), card width (width of virtual vehicle), Gauss _ X (X in gaussian plane coordinate system), Gauss _ Y (Y in gaussian plane coordinate system), Speed _ X (Speed in X axis direction), Speed _ Y (Speed in Y axis direction), Accel _ X (acceleration in X axis direction), Accel _ Y (acceleration in Y axis direction), card Accel (acceleration of vehicle), TurnSig (turning or not), and yawng (heading angle). And then the program and the simulation software on the vehicle respectively read data from the corresponding tables, so that data interaction between the real vehicle and the simulation software TSimactor is realized.
And (3) continuously reading the position, speed, acceleration, heading angle, vehicle length and vehicle width data of the real vehicle from the database by the TSimarator, and generating a digital twin of the real vehicle on the simulation road network in real time according to the data, wherein as shown in fig. 6, the vehicle circled in the figure is the digital twin of the real vehicle, and the motion state of the digital twin in the simulation software is consistent with the motion state of the real vehicle. In addition, the program on the real vehicle also continuously reads the relevant data of the simulated vehicle from the database, stores the data into the state linked list of the other vehicle, then performs conflict judgment according to the information of the other vehicle, generates a corresponding resolution strategy, and controls the real vehicle according to the generated resolution strategy, wherein the interface when the real vehicle runs is shown in fig. 7. Therefore, the purpose of mutual influence between the virtual vehicle and the real test vehicle is achieved.
And (4) analyzing the position, the speed, the acceleration and the course angle of the real vehicle. And comparing the target position, speed, acceleration and course angle of a control algorithm in the simulation software. And evaluating a control algorithm in the simulation software according to the deviation between the actual data and the target position, speed, acceleration and course angle.
The above steps describe the implementation of the present invention in detail, but the present invention is not limited to the details of the above embodiments. Within the scope of the inventive concept, it should not be excluded from the scope of the invention.
Claims (5)
1. An automatic driving simulation test method for interactive mapping of real vehicles and virtual vehicles is characterized by comprising the following steps:
step 1, constructing a test scene in simulation software, and then randomly selecting two corresponding points to determine a coordinate transformation relation between an actual test site and a simulation road network;
step 2, based on the test scene constructed in the step 1, realizing data interaction between the real vehicle and the simulated vehicle through a database, constructing a digital twin body corresponding to the real vehicle in the simulation software according to the transmitted data, wherein the running state of the digital twin body in the simulation software is consistent with that of the real vehicle;
step 3, performing conflict judgment according to the information of other vehicles obtained by data interaction in the step 2, generating corresponding resolution strategies, and controlling the real vehicle according to the generated resolution strategies, so as to achieve the purpose of mutual influence between the virtual vehicle and the real test vehicle;
and 4, storing the track data in the running process of the real vehicle into a database, and analyzing the track data of the actual running of the real vehicle so as to verify and evaluate the actual effect of various control algorithms in the simulation software.
2. The method as claimed in claim 1, wherein step 1 is to select any actual road according to the test requirement, construct a matched simulation road network in the simulation software according to the geometric data, collect the GPS coordinates of any two points in the test site, convert the GPS coordinates into coordinates in the gaussian plane coordinate system, and determine the coordinate conversion relationship between the actual coordinates and the simulation coordinates through the coordinate system transformation formula in combination with the coordinates of the two points in the simulation road network.
3. The method as claimed in claim 1, wherein in step 2, the real vehicle collects position, speed, acceleration and course angle data through sensors mounted on the vehicle, and transmits the data to the table in the database after necessary conversion according to the coordinate conversion relation, the simulation vehicle in the simulation software also continuously converts the vehicle state data and transmits the data to the table in the database during operation, and then the real vehicle and the simulation program respectively read the data from the two tables to complete data interaction between the real vehicle and the simulation vehicle.
4. The method according to claim 1, wherein in the operation process, the simulation software continuously reads the position, speed, acceleration, heading angle, vehicle length and vehicle width data of the real vehicle from the database, and generates the digital twin of the real vehicle on the simulation road network in real time according to the data, the motion state of the digital twin is consistent with the motion state of the real vehicle, and the program on the real vehicle also continuously reads the relevant data of the simulation vehicle from the database, stores the data into the state linked list of the other vehicle, then performs conflict judgment according to the information of the other vehicle, generates a corresponding resolution strategy, and controls the real vehicle according to the generated resolution strategy, thereby achieving the purpose of mutual influence between the virtual vehicle and the real test vehicle.
5. The method as claimed in claim 1, wherein step 4 is to evaluate the control algorithm in the simulation software by analyzing the position, speed, acceleration, and course angle of the real vehicle, comparing the position, speed, acceleration, and course angle with the target position, speed, acceleration, and course angle of the control algorithm in the simulation software, and evaluating the control algorithm in the simulation software by the deviation between the actual data and the target position, speed, acceleration, and course angle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110952185.6A CN113777952A (en) | 2021-08-19 | 2021-08-19 | Automatic driving simulation test method for interactive mapping of real vehicle and virtual vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110952185.6A CN113777952A (en) | 2021-08-19 | 2021-08-19 | Automatic driving simulation test method for interactive mapping of real vehicle and virtual vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113777952A true CN113777952A (en) | 2021-12-10 |
Family
ID=78838184
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110952185.6A Pending CN113777952A (en) | 2021-08-19 | 2021-08-19 | Automatic driving simulation test method for interactive mapping of real vehicle and virtual vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113777952A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114415621A (en) * | 2021-12-13 | 2022-04-29 | 山东省科学院自动化研究所 | Automatic driving real vehicle hybrid test system and method based on virtual scene |
| CN114488851A (en) * | 2022-01-18 | 2022-05-13 | 襄阳达安汽车检测中心有限公司 | Automatic driving test method, device and system based on digital twin technology |
| CN116244886A (en) * | 2022-11-29 | 2023-06-09 | 北京瑞风协同科技股份有限公司 | Virtual-real test data matching method and system |
| WO2023207016A1 (en) * | 2022-04-29 | 2023-11-02 | 长安大学 | Autonomous driving test system and method based on digital twin cloud control platform |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200065443A1 (en) * | 2017-05-02 | 2020-02-27 | The Regents Of The University Of Michigan | Simulated vehicle traffic for autonomous vehicles |
| US20200209874A1 (en) * | 2018-12-31 | 2020-07-02 | Chongqing Jinkang New Energy Vehicle, Ltd. | Combined virtual and real environment for autonomous vehicle planning and control testing |
| CN112907986A (en) * | 2021-01-12 | 2021-06-04 | 浙江大学 | Dynamic time window crossing scheduling method based on digital twin scene and edge cloud |
| CN112925291A (en) * | 2021-01-22 | 2021-06-08 | 大连理工大学 | Digital twin automatic driving test method based on camera dark box |
| CN113051765A (en) * | 2021-03-31 | 2021-06-29 | 中国科学院合肥物质科学研究院 | Intelligent driving vehicle road on-loop test method based on virtual scene change |
| US20210197851A1 (en) * | 2019-12-30 | 2021-07-01 | Yanshan University | Method for building virtual scenario library for autonomous vehicle |
| CN113126618A (en) * | 2021-03-17 | 2021-07-16 | 中国科学院合肥物质科学研究院 | Unmanned global path planning and re-planning method in cross-country environment |
-
2021
- 2021-08-19 CN CN202110952185.6A patent/CN113777952A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200065443A1 (en) * | 2017-05-02 | 2020-02-27 | The Regents Of The University Of Michigan | Simulated vehicle traffic for autonomous vehicles |
| US20200209874A1 (en) * | 2018-12-31 | 2020-07-02 | Chongqing Jinkang New Energy Vehicle, Ltd. | Combined virtual and real environment for autonomous vehicle planning and control testing |
| US20210197851A1 (en) * | 2019-12-30 | 2021-07-01 | Yanshan University | Method for building virtual scenario library for autonomous vehicle |
| CN112907986A (en) * | 2021-01-12 | 2021-06-04 | 浙江大学 | Dynamic time window crossing scheduling method based on digital twin scene and edge cloud |
| CN112925291A (en) * | 2021-01-22 | 2021-06-08 | 大连理工大学 | Digital twin automatic driving test method based on camera dark box |
| CN113126618A (en) * | 2021-03-17 | 2021-07-16 | 中国科学院合肥物质科学研究院 | Unmanned global path planning and re-planning method in cross-country environment |
| CN113051765A (en) * | 2021-03-31 | 2021-06-29 | 中国科学院合肥物质科学研究院 | Intelligent driving vehicle road on-loop test method based on virtual scene change |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114415621A (en) * | 2021-12-13 | 2022-04-29 | 山东省科学院自动化研究所 | Automatic driving real vehicle hybrid test system and method based on virtual scene |
| CN114488851A (en) * | 2022-01-18 | 2022-05-13 | 襄阳达安汽车检测中心有限公司 | Automatic driving test method, device and system based on digital twin technology |
| CN114488851B (en) * | 2022-01-18 | 2023-08-22 | 襄阳达安汽车检测中心有限公司 | Automatic driving test method, device and system based on digital twin technology |
| WO2023207016A1 (en) * | 2022-04-29 | 2023-11-02 | 长安大学 | Autonomous driving test system and method based on digital twin cloud control platform |
| CN116244886A (en) * | 2022-11-29 | 2023-06-09 | 北京瑞风协同科技股份有限公司 | Virtual-real test data matching method and system |
| CN116244886B (en) * | 2022-11-29 | 2024-03-15 | 北京瑞风协同科技股份有限公司 | Virtual-real test data matching method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113777952A (en) | Automatic driving simulation test method for interactive mapping of real vehicle and virtual vehicle | |
| CN111897305B (en) | Data processing method, device, equipment and medium based on automatic driving | |
| US11755396B2 (en) | Generating autonomous vehicle simulation data from logged data | |
| CN112100856B (en) | Automatic driving joint simulation method based on multiple platforms | |
| CN112286206B (en) | Automatic driving simulation method, system, equipment, readable storage medium and platform | |
| CN114879631A (en) | Automatic driving test system and method based on digital twin cloud control platform | |
| CN109461342B (en) | Teaching system for unmanned motor vehicle and teaching method thereof | |
| CN113484851B (en) | Simulation test system and method for vehicle-mounted laser radar and complete vehicle in-loop test system | |
| CN112035951A (en) | Simulation platform and simulation method for automatic driving algorithm verification | |
| CN115185205A (en) | Intelligent driving simulation method, system, terminal device and readable storage medium | |
| WO2021146906A1 (en) | Test scenario simulation method and apparatus, computer device, and storage medium | |
| Shi et al. | An integrated traffic and vehicle co-simulation testing framework for connected and autonomous vehicles | |
| CN114365108A (en) | Automatic driving vehicle simulation method under virtual environment | |
| Bosello et al. | Train in austria, race in montecarlo: Generalized rl for cross-track f1 tenth lidar-based races | |
| Cantas et al. | Customized co-simulation environment for autonomous driving algorithm development and evaluation | |
| CN111983934B (en) | Unmanned vehicle simulation test case generation method and system | |
| Artunedo et al. | Advanced co-simulation framework for cooperative maneuvers among vehicles | |
| Cheng et al. | An Indoor Rapid Testing Platform for Autonomous Vehicles Using Vehicle-in-the-Loop Simulation | |
| Sun et al. | An intelligent driving simulation platform: architecture, implementation and application | |
| US20220058318A1 (en) | System for performing an xil-based simulation | |
| Du et al. | Design of Interacting Multiple Model with Unscented Kalman Filter for V2X Test | |
| Liang et al. | Research on Navigation Recognition Optimization of Unmanned Self-Built Map | |
| CN117648389A (en) | Map construction method, map construction device, electronic equipment and storage medium | |
| Durukal et al. | A Digital Twin Study: Particle Swarm Optimization of ACC Controller for Follow Acceleration Maneuver | |
| CN117909223A (en) | Automatic driving simulation test method, device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |