CN114326443B - MIL simulation test method and system for ADAS and readable storage medium - Google Patents
MIL simulation test method and system for ADAS and readable storage medium Download PDFInfo
- Publication number
- CN114326443B CN114326443B CN202210044955.1A CN202210044955A CN114326443B CN 114326443 B CN114326443 B CN 114326443B CN 202210044955 A CN202210044955 A CN 202210044955A CN 114326443 B CN114326443 B CN 114326443B
- Authority
- CN
- China
- Prior art keywords
- model
- simulation
- vehicle
- adas
- simulation scene
- 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.)
- Active
Links
Abstract
The invention particularly relates to an MIL simulation test method and system for ADAS and a readable storage medium. The method comprises the following steps: constructing a simulation scene model and acquiring simulation scene information; constructing a dynamics model for simulating the response of the bicycle; the ADAS algorithm to be tested is used as a tested model to be respectively connected with the simulation scene model and the dynamic model, and the simulation scene model is connected with the dynamic model to form a model interface closed loop; generating a driving control instruction, inputting the driving control instruction into a dynamics model, and generating corresponding whole vehicle state parameters; and inputting the simulation scene information and the whole vehicle state parameters into a tested model, generating a corresponding control request instruction through the tested model, and inputting the control request instruction into a dynamics model to realize simulation test of the ADAS algorithm to be tested. The invention also correspondingly discloses a simulation test system and a readable storage medium. The MIL simulation test method can be used for rapidly verifying the ADAS algorithm in the early stage of development and performing rapid iteration test after algorithm correction.
Description
Technical Field
The invention relates to the technical field of ADAS simulation test, in particular to an MIL simulation test method and system for ADAS and a readable storage medium.
Background
With the development of the intelligent networking automobile industry, an Advanced Driving Assistance System (ADAS) gradually becomes a standard configuration of an automobile driving system, and is a hot spot for research of the automobile industry in recent years. The verification of the collision avoidance capability of a vehicle under dangerous working conditions in the driving process is the core of ADAS active safety field test. The dangerous working conditions mainly comprise a large number of scenes such as severe weather environments, complex road traffic conditions, typical traffic accidents and the like, and the dangerous working condition scenes are key parts for verifying safe driving control strategies in the automatic driving automobile testing process.
The existing ADAS ECU testing system does not use an automatic mode for testing, and has lower testing efficiency. For this reason, chinese patent publication No. CN110412374a discloses a multisensor-based ADAS HIL test system, which includes an ADAS scene simulation host, a video signal injection module, an ultrasonic signal injection module, an ADAS ECU controller, and a real-time industrial controller. The ADAS hardware-in-loop test system based on the multiple sensors can test a plurality of ADAS ECUs in a loop simulation mode, supported simulation sensors comprise cameras, millimeter wave radars, ultrasonic radars and laser radars, and sensor models in the test system can be configured in an ADAS scene simulation host to simulate sensors of different types and parameters.
The ADAS HIL test system in the prior proposal ensures that various scene test results of the ADAS ECU can be reflected on the scene simulation host, and the test process uses automatic test, thereby having higher test efficiency. The HIL test (controller hardware in loop test) has the advantage of being capable of verifying the overall behavior of the controller more completely, including underlying software, application layer functions, communication drivers, etc., but the disadvantage of this test approach is too dependent on the maturity of the controller. However, for ADAS algorithm development, it is more desirable to perform test verification of the ADAS algorithm before the controller hardware is ready, i.e., MILs test (model-in-loop test), so that the problem of the algorithm (software) can be leaked out early in development, so as to perform rapid iterative optimization, thereby improving development efficiency. Therefore, how to design a method for rapidly verifying the ADAS algorithm in early stage of its development is a technical problem to be solved.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to solve the technical problems that: how to provide an MIL simulation test method for ADAS, so as to be capable of rapidly verifying the ADAS algorithm in the early stage of its development and performing rapid iterative test after algorithm correction, thereby improving the development efficiency of the ADAS algorithm.
In order to solve the technical problems, the invention adopts the following technical scheme:
an MIL simulation test method for ADAS comprises the following steps:
s1: constructing a simulation scene model and acquiring corresponding simulation scene information;
s2: constructing a dynamics model for simulating the response of the bicycle;
s3: the ADAS algorithm to be tested is used as a tested model to be respectively connected with the simulation scene model and the dynamic model, and the simulation scene model is connected with the dynamic model to form a model interface closed loop;
s4: generating a driving control instruction based on the simulation scene model and inputting the driving control instruction into the dynamic model, so that the dynamic model can finish response based on the driving control instruction and generate corresponding whole vehicle state parameters;
s5: the simulation scene information and the whole vehicle state parameters are input into a tested model, a corresponding control request instruction is generated through the tested model and is input into a dynamic model, so that the dynamic model can complete response based on the control request instruction, and simulation test of an ADAS algorithm to be tested is realized.
Preferably, in step S1, the unmanned aerial vehicle simulation software constructs a simulation scene model.
Preferably, in step S1, the simulation scene information includes, but is not limited to, road environment information, target vehicle information, own vehicle information, traffic sign information, and traffic flow information; road environment information includes, but is not limited to, lane line type and road curvature; the target vehicle information includes, but is not limited to, a target vehicle type, a target vehicle relative distance, a target vehicle relative speed, and a target vehicle trajectory; the own vehicle information includes, but is not limited to, an own vehicle relative speed and an own vehicle running track.
Preferably, in step S1, when the simulation scene model is constructed, the sensor of the own vehicle can be configured and the sensor parameters can be customized.
Preferably, in step S2, a dynamics model is built based on the simulation software of the automobile system.
Preferably, in step S4, the driving control instruction includes, but is not limited to, an accelerator opening degree, a braking force magnitude request, and a steering angle request.
Preferably, in step S4, the vehicle state parameters include, but are not limited to, vehicle speed, vehicle acceleration, vehicle wheel speed signal, vehicle yaw rate, vehicle steering angle, and vehicle brake pedal state.
Preferably, in step S4, the dynamics model is further used to generate a vehicle running gesture and input the vehicle running gesture to the simulation scene model, so that the simulation scene model can realize visual display of the vehicle running gesture.
The invention also discloses an MIL simulation test system for ADAS, which is implemented based on the MIL simulation test method of the invention, and specifically comprises the following steps:
the unmanned simulation module is used for constructing a simulation scene model, acquiring corresponding simulation scene information and generating a driving control instruction based on the simulation scene model;
the automobile system simulation module is used for constructing a dynamics model for simulating the response of the automobile, and completing the response based on the driving control instruction through the dynamics model to generate corresponding state parameters of the whole automobile;
the measured and calculated module is used for generating a corresponding control request instruction according to the simulation scene information and the whole vehicle state parameter, and inputting the control request instruction into the automobile system simulation module so that the dynamic model can respond based on the control request instruction.
The invention also discloses a readable storage medium, on which a computer management program is stored, which when being executed by a processor, implements the steps of the MIL simulation test method for ADAS of the invention.
Compared with the prior art, the MIL simulation test method for ADAS has the following beneficial effects:
according to the invention, a simulation scene model and a dynamics model are constructed and form a model interface closed loop with an ADAS algorithm to be tested, so that MIL simulation test of the ADAS algorithm is realized in a simulation response mode, the ADAS algorithm can be rapidly verified in the early stage of development, and rapid iteration test is performed after algorithm correction, so that the development efficiency of ADAS can be improved. Meanwhile, the model interface closed-loop framework is simple in structure and fast in data flow, and MIL simulation test efficiency of an ADAS algorithm can be improved. In addition, the invention generates the whole vehicle state parameter through the driving control instruction, and further generates the control request instruction through the simulation scene information and the whole vehicle state parameter, so that the simulation test of the ADAS algorithm can be effectively realized.
Drawings
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the accompanying drawings, in which:
FIG. 1 is a logic block diagram of an MIL simulation test method for ADAS;
FIG. 2 is a schematic diagram of a model interface closed loop;
fig. 3 is a schematic diagram of an AEB algorithm simulation test experiment.
Detailed Description
The following is a further detailed description of the embodiments:
embodiment one:
the embodiment discloses an MIL simulation test method for ADAS.
As shown in fig. 1, the MILs simulation test method for ADAS includes the following steps:
s1: constructing a simulation scene model and acquiring corresponding simulation scene information;
s2: constructing a dynamics model for simulating the response of the bicycle;
s3: an ADAS (advanced driving assistance system) algorithm to be tested is used as a tested model to be respectively connected with a simulation scene model and a dynamic model, and the simulation scene model is connected with the dynamic model to form a model interface closed loop shown in figure 2;
s4: generating a driving control instruction based on the simulation scene model and inputting the driving control instruction into the dynamic model, so that the dynamic model can finish response based on the driving control instruction and generate corresponding whole vehicle state parameters;
s5: the simulation scene information and the whole vehicle state parameters are input into a tested model, a corresponding control request instruction is generated through the tested model and is input into a dynamic model, so that the dynamic model can complete response based on the control request instruction, and simulation test of an ADAS algorithm to be tested is realized.
It should be noted that, the MILs simulation test method of the present invention can generate corresponding software codes or software services in a program programming manner, and can further be run and implemented on a server and a computer.
According to the invention, a simulation scene model and a dynamics model are constructed and form a model interface closed loop with an ADAS algorithm to be tested, so that MIL simulation test of the ADAS algorithm is realized in a simulation response mode, the ADAS algorithm can be rapidly verified in the early stage of development, and rapid iteration test is performed after algorithm correction, so that the development efficiency of ADAS can be improved. Meanwhile, the model interface closed-loop framework is simple in structure and fast in data flow, and MIL simulation test efficiency of an ADAS algorithm can be improved. In addition, the invention generates the whole vehicle state parameter through the driving control instruction, and further generates the control request instruction through the simulation scene information and the whole vehicle state parameter, so that the simulation test of the ADAS algorithm can be effectively realized.
Specifically, the ADAS algorithm includes, but is not limited to, AEB algorithm, LKA algorithm, ELKA algorithm, and LDW algorithm, and each algorithm is developed based on simulink and operates in a simulink environment.
Specifically, the simulation scene information includes, but is not limited to, road environment information, target vehicle information, own vehicle information, traffic sign information, and traffic flow information; road environment information includes, but is not limited to, lane line type and road curvature; the target vehicle information includes, but is not limited to, a target vehicle type, a target vehicle relative distance, a target vehicle relative speed, and a target vehicle trajectory; the own vehicle information includes, but is not limited to, an own vehicle relative speed and an own vehicle running track.
Specifically, when the simulation scene model is constructed, the sensor of the own vehicle can be configured and the sensor parameters can be customized.
Specifically, the driving control instructions include, but are not limited to, an accelerator opening, a braking force magnitude request, and a steering angle request.
Specifically, the vehicle state parameters include, but are not limited to, vehicle speed, vehicle acceleration, vehicle wheel speed signals, vehicle yaw rate, vehicle steering angle, and vehicle brake pedal state.
In the implementation process, the dynamic model is also used for generating the running gesture of the vehicle and inputting the running gesture into the simulation scene model, so that the simulation scene model can realize the visual display of the running gesture of the vehicle.
In the specific implementation process, a simulation scene model is built based on prescan software (unmanned simulation software), and a corresponding prescan module is generated in a simulink environment. Prescan is based on Matlab simulation platform, and supports traffic scene modeling, sensor modeling, driver behavior modeling and the like, wherein the traffic scene comprises a road model, an environment model, a road user, weather illumination and the like, and the sensor model comprises various cameras, millimeter wave radars, laser radars and the like.
In the specific implementation process, a dynamics model is built based on a Carsim software (automobile system simulation software), and a corresponding Carsim dynamics module is generated in a simulink environment. The Carsim software (dynamics module) can support 27 degrees of freedom, can well simulate the response of a vehicle to driver input, road surface input and aerodynamic input, can truly simulate the response of the vehicle to a driver input instruction or an ADAS algorithm control request instruction, has the characteristics of convenience in use, rapidness in operation, accuracy in simulation, good expansibility and the like, and can be conveniently integrated into a Matlab environment.
According to the MIL simulation test method, the prescan software is used for constructing the simulation scene model, configuring the corresponding sensor and customizing the sensor parameters, so that the accuracy of the MIL simulation test can be effectively ensured. Meanwhile, the dynamic model is built through the Carsim software, the response of the vehicle can be rapidly and accurately simulated, and the accuracy of MIL simulation test can be ensured.
In order to better illustrate the feasibility of the MILs simulation test method of the present invention, the present example discloses the following experiment.
The experiment takes AEB algorithm simulation test as an example, and describes the use flow of an MIL simulation test environment. The test scene is selected from CCRs scenes in the legal test scenes of the CNCAP-AEB, namely, a scene that the target vehicle is stationary and the rear vehicle (own vehicle) and the front vehicle (target vehicle) are in rear-end collision, as shown in fig. 3.
Firstly, constructing a simulation scene:
newly created prescan engineering, and CCRs test scene is built according to figure 3. The scene elements are as follows:
straight road with length of 300 meters, single lane and lane width of 3.5m;
the target vehicle is selected as Audi A3, the speed is 0km/h, and the target vehicle is positioned in the center of the lane and 150m away from the starting point of the lane;
the self-vehicle is selected as Audi A8, and the speed curve is set to be 50km/h to run forwards at a constant speed;
setting a self-vehicle dynamics model as a user definition, and designating an absolute path of a Carsim-Sfuntion file;
adding a radar sensor on the own vehicle, and setting a detection range;
secondly, compiling a scene:
setting the simulation frequency to be 1000 Hz, clicking a compiling button on a toolbar, compiling a scene, and further generating an operation parameter file and a model;
thirdly, invoking simulink:
clicking a invoke Simulink Run Mode button on the toolbar starts matlab and simulink, and opens an automatically generated simulink model;
fourth, adding a Carsim dynamics model:
clicking a simulink library, finding a Carsim function module and dragging the module to an opened simulink model;
fifthly, adding an AEB algorithm module:
adding an AEB algorithm module into the opened simulink model;
sixth, model interface closed loop:
interface between Prescan module and Carsim dynamics module:
referring to fig. 2, driving control instructions, i.e., accelerator opening, braking force, steering request angle signals, output from the Prescan driver model module are connected to an input port of Carsim; the vehicle running gesture output by the Carsim dynamics module is fed back to the Prescan module in real time, namely signals such as the speed, the wheel speed and Roll, pitch, yaw are connected to a receiving module corresponding to the Prescan module;
the Prescan module interfaces with the AEB algorithm module:
referring to fig. 2, the simulation scene information output by the Prescan module is connected to a target input port of the AEB algorithm module;
interface between Carsim dynamics module and AEB algorithm module
Referring to fig. 2, the car dynamics module calculates real-time vehicle state parameters, such as speed, acceleration, wheel speed signal, yaw rate, steering angle, brake pedal state, etc., and connects the control request command request outputted by the AEB algorithm to the input port of the car dynamics module for closed-loop control;
seventh, running a simulation model:
clicking an operation button of the simulink, and operating the true model according to the frequency of 1000 Hz;
eighth step, verifying the operation result:
and observing a function enabling signal and a deceleration strip request signal output by the AEB algorithm module through an oscilloscope module in the simulink, and verifying whether the AEB function algorithm is triggered when the own vehicle approaches the front stationary vehicle at a speed of 50 km/h.
Embodiment two:
the embodiment discloses an MIL simulation test system for ADAS.
The MIL simulation test system for ADAS is implemented based on the MIL simulation test method of the invention, and comprises the following steps:
the prescan module (unmanned simulation module) is used for constructing a simulation scene model, acquiring corresponding simulation scene information and generating a driving control instruction based on the simulation scene model;
the vehicle dynamics module (automobile system simulation module) is used for constructing a dynamics model for simulating the response of the vehicle, and completing the response based on the driving control instruction through the dynamics model to generate corresponding vehicle state parameters;
and the estimated algorithm module (ADAS algorithm module) is used for generating a corresponding control request instruction according to the simulation scene information and the whole vehicle state parameter, and inputting the control request instruction into the Carsim dynamics module so that the dynamics model can respond based on the control request instruction.
It should be noted that, the MILs simulation test system of the present invention operates in a simulink operating environment, where the ADAS algorithm module is connected to the simulation scene model and the dynamics model, respectively, and connects the simulation scene model and the dynamics model to form a model interface closed loop as shown in fig. 2.
According to the invention, a prescan module and a Carsim dynamics module are used for constructing a simulation scene model and a dynamics model, and a model interface closed loop is formed with an ADAS algorithm module, so that MIL simulation test of an ADAS algorithm is realized in a simulated response mode, the ADAS algorithm can be rapidly verified in early stage of development, and rapid iteration test is performed after algorithm correction, so that development efficiency of the ADAS can be improved. Meanwhile, the model interface closed-loop framework is simple in structure and fast in data flow, and MIL simulation test efficiency of an ADAS algorithm can be improved. In addition, the invention generates the whole vehicle state parameter through the driving control instruction, and further generates the control request instruction through the simulation scene information and the whole vehicle state parameter, so that the simulation test of the ADAS algorithm can be effectively realized.
Embodiment III:
the embodiment discloses a readable storage medium, on which a computer management class program is stored, which when executed by a processor, implements the steps of the MILs simulation test method for ADAS of the present invention. The readable storage medium may be a device such as a usb disk or a computer having a readable storage function.
Finally, it should be noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the technical solution, and those skilled in the art should understand that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the present invention, and all such modifications and equivalents are included in the scope of the claims.
Claims (8)
1. The MIL simulation test method for the ADAS is characterized by comprising the following steps of:
s1: constructing a simulation scene model and acquiring corresponding simulation scene information;
s2: constructing a dynamics model for simulating the response of the bicycle;
s3: the ADAS algorithm to be tested is used as a tested model to be respectively connected with the simulation scene model and the dynamic model, and the simulation scene model is connected with the dynamic model to form a model interface closed loop;
s4: generating a driving control instruction based on the simulation scene model and inputting the driving control instruction into the dynamic model, so that the dynamic model can finish response based on the driving control instruction and generate corresponding whole vehicle state parameters;
s5: the simulation scene information and the whole vehicle state parameters are input into a tested model, a corresponding control request instruction is generated through the tested model and is input into a dynamic model, so that the dynamic model can complete response based on the control request instruction, and simulation test and verification of the ADAS algorithm to be tested are realized in early development stage;
the driving control instruction comprises an accelerator opening, a braking force magnitude request and a steering angle request;
the vehicle state parameters include vehicle speed, vehicle acceleration, vehicle wheel speed signals, vehicle yaw rate, vehicle steering angle, and vehicle brake pedal state.
2. The MILs simulation test method for ADAS of claim 1, wherein: in step S1, a simulation scene model is constructed based on unmanned driving simulation software.
3. The MILs simulation test method for ADAS of claim 1, wherein: in step S1, the simulation scene information includes, but is not limited to, road environment information, target vehicle information, own vehicle information, traffic sign information, and traffic flow information; road environment information includes, but is not limited to, lane line type and road curvature; the target vehicle information includes, but is not limited to, a target vehicle type, a target vehicle relative distance, a target vehicle relative speed, and a target vehicle trajectory; the own vehicle information includes, but is not limited to, an own vehicle relative speed and an own vehicle running track.
4. The MILs simulation test method for ADAS of claim 1, wherein: in step S1, when the simulation scene model is constructed, the sensor of the own vehicle can be configured and the sensor parameters can be customized.
5. The MILs simulation test method for ADAS of claim 1, wherein: in step S2, a dynamics model is built based on the automobile system simulation software.
6. The MILs simulation test method for ADAS of claim 1, wherein: in step S4, the dynamics model is further configured to generate a vehicle running gesture and input the vehicle running gesture to the simulation scene model, so that the simulation scene model can realize visual display of the vehicle running gesture.
7. An MILs simulation test system for ADAS, characterized by being implemented based on the MILs simulation test method of claim 1, comprising:
the unmanned simulation module is used for constructing a simulation scene model, acquiring corresponding simulation scene information and generating a driving control instruction based on the simulation scene model;
the automobile system simulation module is used for constructing a dynamics model for simulating the response of the automobile, and completing the response based on the driving control instruction through the dynamics model to generate corresponding state parameters of the whole automobile;
the measured and calculated module is used for generating a corresponding control request instruction according to the simulation scene information and the whole vehicle state parameter, and inputting the control request instruction into the automobile system simulation module so that the dynamic model can respond based on the control request instruction.
8. A readable storage medium, having stored thereon a computer management class program which, when executed by a processor, implements the steps of the MILs simulation test method for ADAS of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210044955.1A CN114326443B (en) | 2022-01-14 | 2022-01-14 | MIL simulation test method and system for ADAS and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210044955.1A CN114326443B (en) | 2022-01-14 | 2022-01-14 | MIL simulation test method and system for ADAS and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114326443A CN114326443A (en) | 2022-04-12 |
| CN114326443B true CN114326443B (en) | 2023-09-29 |
Family
ID=81027368
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210044955.1A Active CN114326443B (en) | 2022-01-14 | 2022-01-14 | MIL simulation test method and system for ADAS and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114326443B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110333730A (en) * | 2019-08-12 | 2019-10-15 | 安徽江淮汽车集团股份有限公司 | Verification method, platform and the storage medium of automatic Pilot algorithm expectation function safety |
| CN110673590A (en) * | 2019-10-21 | 2020-01-10 | 安徽江淮汽车集团股份有限公司 | Method, device and equipment for judging reliability of automatic driving system and storage medium |
| 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 |
| CN110794813A (en) * | 2019-11-18 | 2020-02-14 | 上海顺试汽车科技有限公司 | In-loop real-time linkage testing method and system for electromechanical parts |
| CN112698582A (en) * | 2020-12-28 | 2021-04-23 | 联创汽车电子有限公司 | ADAS ECU simulation test method and system |
| WO2021089787A1 (en) * | 2019-11-08 | 2021-05-14 | Zf Friedrichshafen Ag | Method, apparatus and computer program for enabling a sensor system for detecting objects in an environment of a vehicle |
| CN112925221A (en) * | 2021-01-20 | 2021-06-08 | 重庆长安汽车股份有限公司 | Auxiliary driving closed loop test method based on data reinjection |
| CN112987703A (en) * | 2021-05-19 | 2021-06-18 | 北京博科测试系统股份有限公司 | System and method for developing and testing in-loop automatic driving of whole vehicle in laboratory |
| CN113065257A (en) * | 2021-04-08 | 2021-07-02 | 中国第一汽车股份有限公司 | Automatic generation method and device of test case, computer equipment and medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020014683A1 (en) * | 2018-07-13 | 2020-01-16 | Kache.AI | Systems and methods for autonomous object detection and vehicle following |
-
2022
- 2022-01-14 CN CN202210044955.1A patent/CN114326443B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110333730A (en) * | 2019-08-12 | 2019-10-15 | 安徽江淮汽车集团股份有限公司 | Verification method, platform and the storage medium of automatic Pilot algorithm expectation function safety |
| CN110673590A (en) * | 2019-10-21 | 2020-01-10 | 安徽江淮汽车集团股份有限公司 | Method, device and equipment for judging reliability of automatic driving system and storage medium |
| 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 |
| WO2021089787A1 (en) * | 2019-11-08 | 2021-05-14 | Zf Friedrichshafen Ag | Method, apparatus and computer program for enabling a sensor system for detecting objects in an environment of a vehicle |
| CN110794813A (en) * | 2019-11-18 | 2020-02-14 | 上海顺试汽车科技有限公司 | In-loop real-time linkage testing method and system for electromechanical parts |
| CN112698582A (en) * | 2020-12-28 | 2021-04-23 | 联创汽车电子有限公司 | ADAS ECU simulation test method and system |
| CN112925221A (en) * | 2021-01-20 | 2021-06-08 | 重庆长安汽车股份有限公司 | Auxiliary driving closed loop test method based on data reinjection |
| CN113065257A (en) * | 2021-04-08 | 2021-07-02 | 中国第一汽车股份有限公司 | Automatic generation method and device of test case, computer equipment and medium |
| CN112987703A (en) * | 2021-05-19 | 2021-06-18 | 北京博科测试系统股份有限公司 | System and method for developing and testing in-loop automatic driving of whole vehicle in laboratory |
Non-Patent Citations (1)
| Title |
|---|
| 基于Prescan的自然驾驶场景构建与研究;庄琼倩，等;《汽车实用技术》;第46卷(第07期);30-31 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114326443A (en) | 2022-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110333730B (en) | Verification method, platform and storage medium for safety of expected function of automatic driving algorithm | |
| Gietelink et al. | Development of advanced driver assistance systems with vehicle hardware-in-the-loop simulations | |
| CN111795832B (en) | Intelligent driving vehicle testing method, device and equipment | |
| CN112685289A (en) | Scene generation method, and scene-based model in-loop test method and system | |
| Bühler et al. | Evolutionary functional testing | |
| CN109801534A (en) | Driving behavior hardware-in-the-loop test system based on automatic Pilot simulator | |
| CN108446463B (en) | Microcosmic traffic flow collaborative simulation platform, simulation method and safety evaluation method | |
| Gietelink et al. | Development of a driver information and warning system with vehicle hardware-in-the-loop simulations | |
| CN113311727A (en) | Simulation system for automatic driving test | |
| CN112035951A (en) | Simulation platform and simulation method for automatic driving algorithm verification | |
| CN114967499A (en) | Automatic emergency braking simulation test system and test method | |
| Zhu et al. | Millimeter-wave radar in-the-loop testing for intelligent vehicles | |
| Pfeffer et al. | Continuous development of highly automated driving functions with vehicle-in-the-loop using the example of Euro NCAP scenarios | |
| CN112671487A (en) | Vehicle testing method, server and testing vehicle | |
| CN111767630A (en) | Virtual simulation test method and device applied to intelligent driving | |
| CN114326443B (en) | MIL simulation test method and system for ADAS and readable storage medium | |
| US11657635B2 (en) | Measuring confidence in deep neural networks | |
| CN115755865A (en) | Commercial vehicle driving assistance hardware in-loop test system and method | |
| Xu et al. | Driving simulation of autonomous vehicle with ADS control | |
| CN117413257A (en) | Method and system for testing driver assistance system for vehicle | |
| Fan et al. | A Co-Simulation Platform for Powertrain Controls Development | |
| Di Russo et al. | Experimental evaluation of longitudinal control for automated vehicles through vehicle-in-the-loop testing | |
| Zhang et al. | Development and verification of traffic confrontation simulation test platform based on PanoSim | |
| CN111881121A (en) | Automatic driving data filling method and device | |
| CN116562175B (en) | Method for evaluating influence of vehicle configuration on safety of automatic driving system |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |