CN112035951A - Simulation platform and simulation method for automatic driving algorithm verification - Google Patents
Simulation platform and simulation method for automatic driving algorithm verification Download PDFInfo
- Publication number
- CN112035951A CN112035951A CN202010847291.3A CN202010847291A CN112035951A CN 112035951 A CN112035951 A CN 112035951A CN 202010847291 A CN202010847291 A CN 202010847291A CN 112035951 A CN112035951 A CN 112035951A
- Authority
- CN
- China
- Prior art keywords
- automatic driving
- module
- simulation
- driving algorithm
- algorithm
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/15—Vehicle, aircraft or watercraft design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Automation & Control Theory (AREA)
- Aviation & Aerospace Engineering (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention belongs to the technical field of automobiles, and particularly relates to a simulation platform and a simulation method for automatic driving algorithm verification. The simulation platform comprises three parts, an automatic driving environment building module, an automatic driving simulation observation module and an automatic driving algorithm development module. The automatic driving environment building module builds a virtual scene which needs to be verified by an automatic driving algorithm, automatically associates with the automatic driving simulation observation module after the building is finished, and can automatically generate an automatic driving algorithm development module; the automatic driving simulation observation module is used for observing and monitoring the scene generation process in the automatic driving algorithm test process; the automatic driving algorithm development module is mainly used for connecting an automatic driving algorithm input/output interface signal with a simulation scene environment signal, and can operate an automatic driving algorithm in a virtual scene built by the automatic driving environment building module through a specific input/output component to control the action and response of a virtual target vehicle, so that the aim of verifying the automatic driving algorithm is fulfilled.
Description
Technical Field
The invention belongs to the technical field of automobiles, and particularly relates to a simulation platform and a simulation method for automatic driving algorithm verification.
Background
The development of general vehicle software/algorithms follows a process from simulation to real vehicle verification, and autodrive algorithms are no exception. The simulation verification has the advantages of low risk, low cost, high efficiency, fast iteration and the like.
The automatic driving algorithm is characterized by complex scenes and multi-object construction during verification, and a verification platform developed by a traditional algorithm cannot complete the task.
Disclosure of Invention
The invention provides a simulation platform and a simulation method for verification of an automatic driving algorithm, which can realize the construction of a complex scene and multiple objects, can directly access the automatic driving algorithm to the simulation platform, can realize the closed-loop verification of the automatic driving algorithm of the complex scene and the multiple objects, and can directly transplant the automatic driving algorithm and generate codes subsequently, thereby ensuring the consistency of the automatic driving algorithm.
The technical scheme of the invention is described as follows by combining the attached drawings:
a simulation platform for verification of an automatic driving algorithm comprises an automatic driving environment building module 1, an automatic driving simulation observation module 2 and an automatic driving algorithm development module 3; the automatic driving environment building module 1 is used for building a virtual scene which needs to be verified by an automatic driving algorithm, automatically associating the automatic driving simulation observation module after building is finished, and automatically generating an automatic driving algorithm development module; the automatic driving simulation observation module 2 is used for observing and monitoring the scene generation process in the automatic driving algorithm test process; the automatic driving algorithm development module 3 is used for connecting the input/output interface signal of the automatic driving algorithm with the environment signal of the simulation scene, operating the automatic driving algorithm in the virtual scene built by the automatic driving environment building module through a specific input/output component, controlling the action and response of a virtual target vehicle and achieving the purpose of verifying the automatic driving algorithm.
The automatic driving algorithm development module 3 is composed of a dynamic parameter input component 4, a sensor signal input component 5, a virtual road signal input component 6, a path following input component 7, an automatic driving algorithm module 8 and a dynamic parameter output component 9 of a target vehicle, wherein the dynamic parameter input component 4, the sensor signal input component 5, the virtual road signal input component 6 and the path following input component 7 of the target vehicle are used as input components of the automatic driving algorithm module 8, and the dynamic parameter output component 9 of the target vehicle is used as an output part of the automatic driving algorithm module 8.
The dynamic parameter input component 4 of the target vehicle, the input signal of which is from the automatic driving environment, outputs the dynamic parameter of the target vehicle, including the coordinate parameter [ x, y, z ] of the target vehicle in the automatic driving environment, the longitudinal speed of the vehicle, the longitudinal acceleration of the vehicle, the transverse speed of the vehicle, the transverse acceleration of the vehicle, the heading angle of the vehicle, the lateral angular speed of the vehicle, the pitch angular speed of the vehicle, the yaw angular speed of the vehicle and the GPS signal longitude and latitude of the vehicle; the sensor input component 5 is used for inputting signals from an automatic driving environment and outputting information including obstacle coordinates, an obstacle direction angle, an obstacle speed, an obstacle type and an obstacle distance; the virtual road signal input component 6 is used for inputting signals from an automatic driving environment, and outputting signals comprising lane line coordinates, road width, road type, road surface friction coefficient and traffic identification; the path following input component 7, the input signal of which comes from the automatic driving environment, and the output signal of which comprises the vehicle running track and the vehicle running speed which are preset in the automatic driving environment; a target vehicle dynamics parameter output part 9 whose input signals include a target vehicle target gear, a target vehicle target speed, a target vehicle braking request, and a target vehicle target steering angle, which outputs dynamics parameters of the target vehicle to an autonomous driving environment; in the simulation operation process, the data interaction between the automatic driving algorithm development module 3 and the automatic driving simulation observation module 2 forms the closed-loop simulation of the automatic driving algorithm.
A simulation method for a simulation platform for automated driving algorithm verification, comprising the steps of:
step one, building an automatic driving algorithm;
secondly, building a simulation scene through the automatic driving environment building module 1;
step three, associating the simulation scene with the automatic driving simulation observation module 2 through the automatic driving environment building module 1;
step four, generating an automatic driving algorithm development module 3 through the automatic driving environment building module 1;
step five, transplanting an automatic driving algorithm to an automatic driving algorithm development module 2;
and step six, operating the simulation platform.
The specific method of the first step is as follows:
and (3) building an automatic driving algorithm module by using a basic module and a module in a basic algorithm library which are well defined in MATLAB, wherein input variables of the automatic driving algorithm module comprise dynamic parameters, sensor signals, virtual road signals and path following preset signals of the vehicle, and output variables of the automatic driving algorithm module comprise dynamic parameters, transverse parameters, longitudinal control parameters and the like of the vehicle and target steering control parameters of the vehicle.
The specific method of the second step is as follows:
using automatic driving simulation software to build a virtual scene environment for automatic driving algorithm verification, wherein the static aspects are the form of a road, the number and initial state of vehicles, traffic signal lamps and other road marks, the number and height of pedestrians and the design and layout of a building; the dynamic aspect is the running track preplanning of the target vehicle, the running track planning of the environmental vehicle, the pedestrian running track preplanning and the design and layout of the weather change condition.
The concrete method of the third step is as follows:
after the virtual environment scene is built by using the automatic driving environment building module 1, configuration items are set or background scripts are used, and after the completeness of the virtual environment scene is automatically checked, the three-dimensional virtual scene environment of the automatic driving simulation observation module 2 is updated.
The concrete method of the fourth step is as follows:
after the virtual environment scene is built by using the automatic driving environment building module 1, configuration items are set or background scripts are used, after the completeness of the virtual environment scene is automatically checked, a driving algorithm development module 3 is automatically generated, and an input/output module of the module is associated with the automatic driving simulation observation module 2.
The concrete method of the step five is as follows:
packing the automatic driving algorithm developed in the step one into a SubSystems or ModelReference form, adding the packed automatic driving algorithm into the automatic driving algorithm development module 3, connecting the input of the automatic driving algorithm development module 3 with the input of the automatic driving algorithm development module, and connecting the output of the automatic driving algorithm development module 3 with the output of the automatic driving algorithm development module, ensuring that the completeness is kept in the closed-loop simulation of the automatic driving algorithm development module 3 and the automatic driving simulation observation module 2, and optionally adding a signal observer to a target signal line according to the requirements in the transplanting process.
The concrete method of the sixth step is as follows:
clicking a start button in the automatic driving algorithm development module 3 to perform closed-loop simulation of the automatic driving algorithm development module 3 and the automatic driving simulation observation module 2, and judging the passing condition of the automatic driving algorithm verification through the results of the automatic driving simulation observation module 2 and the signal observer in the process; if the judgment is passed, the verification of the automatic driving algorithm is finished, if the judgment is not passed, the automatic driving algorithm is developed or a simulation scene is built, and the process is carried out downwards again.
The invention has the beneficial effects that:
the method can realize the construction of complex scenes and multiple objects, can directly access the automatic driving algorithm to the simulation platform, can realize the closed-loop verification of the automatic driving algorithm of the complex scenes and the multiple objects, and can directly transplant the automatic driving algorithm and generate codes subsequently, thereby ensuring the consistency of the automatic driving algorithm.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments of the present invention will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the contents of the embodiments of the present invention and the drawings without creative efforts.
FIG. 1 is a simulation platform for automated driving algorithm verification in accordance with the present invention.
FIG. 2 is a flow chart of a simulation method for verification of an autopilot algorithm in accordance with the present invention.
In the figure: 1. an automatic driving environment building module; 2. an automatic driving simulation observation module; 3. an automatic driving algorithm development module; 4. a dynamic parameter input component of the target vehicle; 5. a sensor signal input section; 6. a virtual road signal input section; 7. a path-following input section; 8. an automatic driving algorithm module; 9. a dynamic parameter output component of the target vehicle.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Referring to fig. 1, a simulation platform for autodrive algorithm verification includes an autodrive environment building module 1, an autodrive simulation observing module 2, and an autodrive algorithm developing module 3.
The automatic driving environment building module 1 is used for building a virtual scene which needs to be verified by an automatic driving algorithm, automatically associating the automatic driving simulation observation module after building is finished, and automatically generating an automatic driving algorithm development module.
The automatic driving simulation observation module 2 is used for observing and monitoring the scene generation process in the automatic driving algorithm test process.
The automatic driving algorithm development module 3 is used for connecting the input/output interface signal of the automatic driving algorithm with the environment signal of the simulation scene, operating the automatic driving algorithm in the virtual scene built by the automatic driving environment building module through a specific input/output component, controlling the action and response of a virtual target vehicle and achieving the purpose of verifying the automatic driving algorithm. The automatic driving algorithm development module 3 can be connected with different virtual signal observers as required to assist in verifying whether the automatic driving algorithm passes the algorithm function verification of the scene or not; when the automatic driving algorithm can not pass the algorithm function verification of the scene, the solution of the virtual scene environment change based on the automatic driving environment building module meets the following requirements, the changed virtual scene environment automatically updates the original automatic driving algorithm development module, the automatic driving algorithm module in the original automatic driving algorithm development module is reserved, and the original connected input component and output component are not interrupted and are reserved as required.
The automatic driving algorithm development module 3 is composed of a dynamic parameter input component 4, a sensor signal input component 5, a virtual road signal input component 6, a path following input component 7, an automatic driving algorithm module 8 and a dynamic parameter output component 9 of a target vehicle, wherein the dynamic parameter input component 4, the sensor signal input component 5, the virtual road signal input component 6 and the path following input component 7 of the target vehicle are used as input components of the automatic driving algorithm module 8, and the dynamic parameter output component 9 of the target vehicle is used as an output part of the automatic driving algorithm module 8.
The dynamic parameter input component 4 of the target vehicle, the input signal of which is from the automatic driving environment, outputs the dynamic parameter of the target vehicle, including the coordinate parameter [ x, y, z ] of the target vehicle in the automatic driving environment, the longitudinal speed of the vehicle, the longitudinal acceleration of the vehicle, the transverse speed of the vehicle, the transverse acceleration of the vehicle, the heading angle of the vehicle, the lateral angular speed of the vehicle, the pitch angular speed of the vehicle, the yaw angular speed of the vehicle and the GPS signal longitude and latitude of the vehicle; the sensor input component 5 is used for inputting signals from an automatic driving environment and outputting information including obstacle coordinates, an obstacle direction angle, an obstacle speed, an obstacle type and an obstacle distance; the virtual road signal input component 6 is used for inputting signals from an automatic driving environment, and outputting signals comprising lane line coordinates, road width, road type, road surface friction coefficient and traffic identification; the path following input component 7, the input signal of which comes from the automatic driving environment, and the output signal of which comprises the vehicle running track and the vehicle running speed which are preset in the automatic driving environment; a target vehicle dynamics parameter output part 9 whose input signals include a target vehicle target gear, a target vehicle target speed, a target vehicle braking request, and a target vehicle target steering angle, which outputs dynamics parameters of the target vehicle to an autonomous driving environment; in the simulation operation process, the data interaction between the automatic driving algorithm development module 3 and the automatic driving simulation observation module 2 forms the closed-loop simulation of the automatic driving algorithm.
The automatic driving algorithm module is built by a basic module library and a basic algorithm library, the basic module library and the basic algorithm library have reusability and can generate automatic codes under the limitation of different compiled target description files, and the automatic driving algorithm module is integrated into the automatic driving algorithm development module 3 and is used as a part of the automatic driving development module.
Referring to fig. 2, a simulation method of a simulation platform for verification of an autopilot algorithm includes the steps of:
step one, building an automatic driving algorithm;
for example, an automatic parking algorithm is constructed by using a basic module defined in MATLAB and a module in a basic algorithm library, wherein input variables of the automatic parking algorithm comprise vehicle dynamics parameters, sensor signals, virtual road signals, path following preset signals and the like, and output variables of the automatic parking algorithm comprise vehicle dynamics parameters, vehicle transverse parameters, longitudinal control parameters and the like, and target steering control parameters of the vehicle, such as target steering control parameters of the vehicle.
Secondly, building a simulation scene through the automatic driving environment building module 1;
using general automatic driving simulation software including but not limited to CarSim, AirSim, Prescan and the like to build a virtual scene environment for automatic driving algorithm verification, wherein the static aspects are road form, vehicle number and initial state, road marks such as traffic lights and the like, pedestrian number and height, and design and layout of buildings; the dynamic aspect is the running track preplanning of the target vehicle, the running track planning of the environmental vehicle, the pedestrian running track preplanning and the design and layout of the weather change condition.
Step three, associating the simulation scene with the automatic driving simulation observation module 2 through the automatic driving environment building module 1;
the autopilot simulation observation module 2 may be based on general autopilot simulation software including, but not limited to, CarSim, AirSim, PreScan, etc.
After the virtual environment scene is built by using the automatic driving environment building module 1, configuration items are set or background scripts are used, and after the completeness of the virtual environment scene is automatically checked, the three-dimensional virtual scene environment of the automatic driving simulation observation module 2 is updated.
Step four, generating an automatic driving algorithm development module 3 through the automatic driving environment building module 1;
the automatic driving algorithm development module 3 is based on MATLAB software, and the format is defined as slx.
After the virtual environment scene is built by using the automatic driving environment building module 1, configuration items are set or background scripts are used, after the completeness of the virtual environment scene is automatically checked, a driving algorithm development module 3 is automatically generated, and an input/output module of the module is associated with the automatic driving simulation observation module 2.
Step five, transplanting an automatic driving algorithm to an automatic driving algorithm development module 2;
packing the automatic driving algorithm developed in the step one into a SubSystems or ModelReference form, adding the packed automatic driving algorithm into the automatic driving algorithm development module 3, connecting the input of the automatic driving algorithm development module 3 with the input of the automatic driving algorithm development module, and connecting the output of the automatic driving algorithm development module 3 with the output of the automatic driving algorithm development module, ensuring that the completeness is kept in the closed-loop simulation of the automatic driving algorithm development module 3 and the automatic driving simulation observation module 2, and optionally adding a signal observer to a target signal line according to the requirements in the transplanting process.
And step six, operating the simulation platform.
The running environment of the simulation platform is a Windows 10 environment.
Clicking a start button in the automatic driving algorithm development module 3 to perform closed-loop simulation of the automatic driving algorithm development module 3 and the automatic driving simulation observation module 2, and judging the passing condition of the automatic driving algorithm verification through the results of the automatic driving simulation observation module 2 and the signal observer in the process; if the judgment is passed, the verification of the automatic driving algorithm is finished, if the judgment is not passed, the automatic driving algorithm is developed or a simulation scene is built, and the process is carried out downwards again.
To sum up, the automatic driving environment building module 1 builds a virtual scene which needs to be verified by the automatic driving algorithm, automatically associates the automatic driving simulation observation module 2 after the building is finished, and can automatically generate the automatic driving algorithm development module 3; the automatic driving simulation observation module 2 is used for observing and monitoring the scene generation process in the automatic driving algorithm test process; the automatic driving algorithm development module 3 is mainly used for connecting an input/output interface signal of an automatic driving algorithm with an environment signal of a simulation scene, and can operate the automatic driving algorithm in a virtual scene built by the automatic driving environment building module through a specific input/output component to control the action and response of a virtual target vehicle, so that the aim of verifying the automatic driving algorithm is fulfilled.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. A simulation platform for verification of an automatic driving algorithm is characterized by comprising an automatic driving environment building module (1), an automatic driving simulation observation module (2) and an automatic driving algorithm development module (3); the automatic driving environment building module (1) is used for building a virtual scene which needs to be verified by an automatic driving algorithm, automatically associating the automatic driving simulation observation module after building is finished, and automatically generating an automatic driving algorithm development module; the automatic driving simulation observation module (2) is used for observing and monitoring the scene generation process in the automatic driving algorithm test process; the automatic driving algorithm development module (3) is used for connecting the input and output interface signals of the automatic driving algorithm with the environment signals of the simulation scene, operating the automatic driving algorithm in the virtual scene built by the automatic driving environment building module through a specific input and output component, controlling the action and response of a virtual target vehicle and achieving the purpose of verifying the automatic driving algorithm.
2. The simulation platform for verification of the automatic driving algorithm according to claim 1, wherein the automatic driving algorithm development module (3) is composed of a dynamic parameter input part (4) of the target vehicle, a sensor signal input part (5), a virtual road signal input part (6), a path following input part (7), an automatic driving algorithm module (8) and a dynamic parameter output part (9) of the target vehicle, wherein the dynamic parameter input part (4) of the target vehicle, the sensor signal input part (5), the virtual road signal input part (6), the path following input part (7) are used as input parts of the automatic driving algorithm module (8), and the dynamic parameter output part (9) of the target vehicle is used as an output part of the automatic driving algorithm module (8).
3. A simulation platform for autopilot algorithm verification according to claim 2 wherein the target vehicle dynamics input component (4) inputs signals from the autopilot environment and the output target vehicle dynamics include the target vehicle's coordinate parameters [ x, y, z ] in the autopilot environment, vehicle longitudinal velocity, vehicle longitudinal acceleration, vehicle lateral velocity, vehicle lateral acceleration, vehicle heading angle, vehicle side angular velocity, vehicle pitch angular velocity, vehicle yaw angular velocity, and vehicle GPS signal latitude and longitude; the sensor input component (5) is used for inputting signals from an automatic driving environment and outputting information comprising obstacle coordinates, an obstacle direction angle, an obstacle speed, an obstacle type and an obstacle distance; the virtual road signal input component (6) is used for inputting signals from an automatic driving environment, and outputting signals comprising lane line coordinates, road width, road type, road surface friction coefficient and traffic identification; the path following input component (7) is used for inputting signals from an automatic driving environment, and outputting signals comprising a vehicle running track and a vehicle running speed which are preset in the automatic driving environment; a target vehicle dynamics parameter output section (9) whose input signals include a target vehicle target gear, a target vehicle target speed, a target vehicle braking request, and a target vehicle target steering angle, and which outputs a target vehicle dynamics parameter to an autonomous driving environment; in the simulation operation process, the data interaction between the automatic driving algorithm development module (3) and the automatic driving simulation observation module (2) forms closed-loop simulation of the automatic driving algorithm.
4. The simulation method of a simulation platform for autodrive algorithm verification according to claim 1, comprising the steps of:
step one, building an automatic driving algorithm;
step two, building a simulation scene through an automatic driving environment building module (1);
step three, associating the simulation scene with the automatic driving simulation observation module (2) through the automatic driving environment building module (1);
step four, generating an automatic driving algorithm development module (3) through an automatic driving environment building module (1);
step five, transplanting an automatic driving algorithm to an automatic driving algorithm development module (2);
and step six, operating the simulation platform.
5. The simulation method of the simulation platform for the verification of the automatic driving algorithm, according to claim 4, is characterized in that the specific method of the first step is as follows:
and (3) building an automatic driving algorithm module by using a basic module and a module in a basic algorithm library which are well defined in MATLAB, wherein input variables of the automatic driving algorithm module comprise dynamic parameters, sensor signals, virtual road signals and path following preset signals of the vehicle, and output variables of the automatic driving algorithm module comprise dynamic parameters, transverse parameters, longitudinal control parameters and the like of the vehicle and target steering control parameters of the vehicle.
6. The simulation method of the simulation platform for the verification of the automatic driving algorithm, according to claim 4, is characterized in that the specific method of the second step is as follows:
using automatic driving simulation software to build a virtual scene environment for automatic driving algorithm verification, wherein the static aspects are the form of a road, the number and initial state of vehicles, traffic signal lamps and other road marks, the number and height of pedestrians and the design and layout of a building; the dynamic aspect is the running track preplanning of the target vehicle, the running track planning of the environmental vehicle, the pedestrian running track preplanning and the design and layout of the weather change condition.
7. The simulation method of the simulation platform for the verification of the automatic driving algorithm, according to claim 4, is characterized in that the specific method of the third step is as follows:
after the virtual environment scene is built by using the automatic driving environment building module (1), configuration items are set or background scripts are used, and after the completeness of the virtual environment scene is automatically checked, the three-dimensional virtual scene environment of the automatic driving simulation observation module (2) is updated.
8. The simulation method of the simulation platform for the verification of the automatic driving algorithm, according to claim 4, is characterized in that the concrete method of the fourth step is as follows:
after the virtual environment scene is built by using the automatic driving environment building module (1), configuration items are set or background scripts are used, after the completeness of the virtual environment scene is automatically checked, a driving algorithm development module (3) is automatically generated, and an input/output module of the driving algorithm development module is associated with the automatic driving simulation observation module (2).
9. The simulation method of the simulation platform for the verification of the automatic driving algorithm, according to claim 4, is characterized in that the concrete method of the fifth step is as follows:
packing the automatic driving algorithm developed in the step one into a SubSystems or ModelReference form, adding the SubSystems or ModelReference form into the automatic driving algorithm development module (3), connecting the input of the automatic driving algorithm development module with the input of the automatic driving algorithm development module (3), connecting the output of the automatic driving algorithm development module with the output of the automatic driving algorithm development module (3), ensuring that the completeness is kept in the closed-loop simulation of the automatic driving algorithm development module (3) and the automatic driving simulation observation module (2), and optionally adding a signal observer to a target signal line according to requirements in the transplanting process.
10. The simulation method of the simulation platform for the verification of the automatic driving algorithm, according to claim 4, is characterized in that the specific method of the sixth step is as follows:
clicking a start button in the automatic driving algorithm development module (3) to perform closed-loop simulation of the automatic driving algorithm development module (3) and the automatic driving simulation observation module (2), wherein the passing condition of the automatic driving algorithm verification is judged according to the results of the automatic driving simulation observation module (2) and the signal observer in the process; if the judgment is passed, the verification of the automatic driving algorithm is finished, if the judgment is not passed, the automatic driving algorithm is developed or a simulation scene is built, and the process is carried out downwards again.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010847291.3A CN112035951A (en) | 2020-08-21 | 2020-08-21 | Simulation platform and simulation method for automatic driving algorithm verification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010847291.3A CN112035951A (en) | 2020-08-21 | 2020-08-21 | Simulation platform and simulation method for automatic driving algorithm verification |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112035951A true CN112035951A (en) | 2020-12-04 |
Family
ID=73580340
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010847291.3A Pending CN112035951A (en) | 2020-08-21 | 2020-08-21 | Simulation platform and simulation method for automatic driving algorithm verification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112035951A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112269325A (en) * | 2020-12-21 | 2021-01-26 | 腾讯科技（深圳）有限公司 | Automatic driving simulation method and device, storage medium and electronic equipment |
| CN112883489A (en) * | 2021-02-05 | 2021-06-01 | 西藏宁算科技集团有限公司 | Automatic driving automobile simulation system |
| CN113126624A (en) * | 2021-04-20 | 2021-07-16 | 禾多科技（北京）有限公司 | Automatic driving simulation test method, device, electronic equipment and medium |
| CN114200849A (en) * | 2021-12-06 | 2022-03-18 | 苏州挚途科技有限公司 | Virtual simulation test system and method for automatic driving |
| CN115167182A (en) * | 2022-09-07 | 2022-10-11 | 禾多科技（北京）有限公司 | Automatic driving simulation test method, device, equipment and computer readable medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108803607A (en) * | 2018-06-08 | 2018-11-13 | 北京领骏科技有限公司 | A kind of multifunction emulation system for automatic Pilot |
| CN110414082A (en) * | 2019-07-09 | 2019-11-05 | 武汉乐庭软件技术有限公司 | A kind of construction method of automatic Pilot decision and control associative simulation model |
| CN110794810A (en) * | 2019-11-06 | 2020-02-14 | 安徽瑞泰智能装备有限公司 | Method for carrying out integrated test on intelligent driving vehicle |
| CN111324044A (en) * | 2018-11-28 | 2020-06-23 | 苏州慧德仿真技术有限公司 | Simulation system and test platform for unmanned automobile |
-
2020
- 2020-08-21 CN CN202010847291.3A patent/CN112035951A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108803607A (en) * | 2018-06-08 | 2018-11-13 | 北京领骏科技有限公司 | A kind of multifunction emulation system for automatic Pilot |
| CN111324044A (en) * | 2018-11-28 | 2020-06-23 | 苏州慧德仿真技术有限公司 | Simulation system and test platform for unmanned automobile |
| CN110414082A (en) * | 2019-07-09 | 2019-11-05 | 武汉乐庭软件技术有限公司 | A kind of construction method of automatic Pilot decision and control associative simulation model |
| CN110794810A (en) * | 2019-11-06 | 2020-02-14 | 安徽瑞泰智能装备有限公司 | Method for carrying out integrated test on intelligent driving vehicle |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112269325A (en) * | 2020-12-21 | 2021-01-26 | 腾讯科技（深圳）有限公司 | Automatic driving simulation method and device, storage medium and electronic equipment |
| CN112269325B (en) * | 2020-12-21 | 2021-03-16 | 腾讯科技（深圳）有限公司 | Automatic driving simulation method and device, storage medium and electronic equipment |
| CN112883489A (en) * | 2021-02-05 | 2021-06-01 | 西藏宁算科技集团有限公司 | Automatic driving automobile simulation system |
| CN113126624A (en) * | 2021-04-20 | 2021-07-16 | 禾多科技（北京）有限公司 | Automatic driving simulation test method, device, electronic equipment and medium |
| CN114200849A (en) * | 2021-12-06 | 2022-03-18 | 苏州挚途科技有限公司 | Virtual simulation test system and method for automatic driving |
| CN115167182A (en) * | 2022-09-07 | 2022-10-11 | 禾多科技（北京）有限公司 | Automatic driving simulation test method, device, equipment and computer readable medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chen et al. | A novel integrated simulation and testing platform for self-driving cars with hardware in the loop | |
| CN112035951A (en) | Simulation platform and simulation method for automatic driving algorithm verification | |
| US11755396B2 (en) | Generating autonomous vehicle simulation data from logged data | |
| WO2023207016A1 (en) | Autonomous driving test system and method based on digital twin cloud control platform | |
| US20190235521A1 (en) | System and method for end-to-end autonomous vehicle validation | |
| Szalay | Next generation X-in-the-loop validation methodology for automated vehicle systems | |
| CN108319249B (en) | Unmanned driving algorithm comprehensive evaluation system and method based on driving simulator | |
| CN108446463B (en) | Microcosmic traffic flow collaborative simulation platform, simulation method and safety evaluation method | |
| Guvenc et al. | Connected and autonomous vehicles | |
| CN112685289A (en) | Scene generation method, and scene-based model in-loop test method and system | |
| CN108508761A (en) | A kind of AEB algorithm function verification methods based on CarMaker simulated environment | |
| CN113918615A (en) | Simulation-based driving experience data mining model construction method and system | |
| Bruggner et al. | Model in the loop testing and validation of embedded autonomous driving algorithms | |
| EP4327052A1 (en) | Systems and methods for simulation supported map quality assurance in an autonomous vehicle context | |
| Solmaz et al. | Hybrid testing: A vehicle-in-the-loop testing method for the development of automated driving functions | |
| WO2021049062A1 (en) | Recognition model distribution system and recognition model updating method | |
| Miura et al. | Converting driving scenario framework for testing self-driving systems | |
| Gowal et al. | A realistic simulator for the design and evaluation of intelligent vehicles | |
| Fan et al. | A Co-Simulation Platform for Powertrain Controls Development | |
| Becker et al. | Bosch's approach toward automated driving | |
| Kanakagiri | Development of a virtual simulation environment for autonomous driving using digital twins | |
| Song et al. | Automatic Driving Joint Simulation Technology and Platform Design | |
| Yabe et al. | Self-driving Simulator Test Scenario Framework with Event-triggered Functionality | |
| Salehi et al. | Application of Munich agile concept for MBSE by means of automated valet parking functions and the 3D environment-data | |
| Ruusiala | Vehicle automation software development using software-only simulation |
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 |