CN116165915A - Virtual test system for testing functions of pedestrian automatic emergency braking system - Google Patents
Virtual test system for testing functions of pedestrian automatic emergency braking system Download PDFInfo
- Publication number
- CN116165915A CN116165915A CN202310185678.0A CN202310185678A CN116165915A CN 116165915 A CN116165915 A CN 116165915A CN 202310185678 A CN202310185678 A CN 202310185678A CN 116165915 A CN116165915 A CN 116165915A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- data
- model
- test
- 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.)
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Traffic Control Systems (AREA)
Abstract
Aiming at the situation that the existing pedestrian automatic emergency braking function test system does not consider traffic scene information in real accidents and has no pertinence to the test in dangerous scenes, the virtual test system for testing the pedestrian automatic emergency braking function is provided, and comprises a control module, a real-time dynamic module, a data monitoring system, a communication module and a display; the control module is used for importing a control strategy and controlling the motion state of a test vehicle, the real-time dynamic module is used for constructing a test scene and a test vehicle model for the test system, the data monitoring system is used for monitoring data information in the test process in real time and displaying output data in real time in the display, the communication module is used for realizing data transmission among the modules, and the display is used for displaying a 3D model of a virtual scene and a test process image; compared with the prior art, the invention has the beneficial effects that: by analyzing the traffic scene characteristics in the real accident, the typical collision scene of the human and the vehicle is extracted, so that the test scene is closer to the real dangerous traffic environment, and the test effect is more accurate and efficient.
Description
Technical Field
The invention relates to the field of intelligent automobiles, in particular to a virtual test system and a virtual test method for the function of an automatic emergency braking system for pedestrians.
Background
In recent years, with the rapid development of the automotive electronics industry, intelligent driving assistance technology is mature, the attention of consumers to the safety of automobiles is continuously improved, a pedestrian automatic emergency braking system detects pedestrians in front of an automobile by using sensors such as radar, and when a potential collision danger between the automobile and the pedestrians is detected, the driver is warned and actively braked to reduce the speed of the automobile, so that collision is effectively avoided, and damage to the pedestrians in accidents can be reduced.
The application of the automatic emergency braking system for pedestrians in intelligent driving automobiles is gradually popularized, and performance test is required to be carried out on the automatic emergency braking system for pedestrians in order to improve the safety of the system. In the related art, the test system of the automatic emergency braking system focuses on the test device, the data record and the like of the automatic braking system, traffic scene information in real accidents is not considered, and the test in dangerous scenes is not effectively analyzed and has no pertinence, so that the evaluation scene of the test of the automatic emergency braking system for pedestrians in the related art is insufficient, the test result is not accurate enough, the performance test effect is not ideal, and improvement is needed.
Disclosure of Invention
In view of this, the invention aims to overcome the defects existing in the prior art, and provides a virtual test system for testing the functions of an automatic emergency braking system for pedestrians, which comprises a test scene and a test method, wherein accident scene elements and typical features are extracted from real accidents by a clustering analysis method, and real traffic accident scenes are reproduced, and the invention adopts the following technical scheme:
a virtual test system for testing functions of an automatic emergency braking system for pedestrians comprises a control module, a real-time dynamic module, a data monitoring system, a communication module and a display, wherein the main functions of the modules are as follows:
the control module is mainly used for inputting a control strategy and controlling a control signal of the test vehicle dynamics model according to the current system data obtained by the control strategy; the real-time dynamic module provides a test platform for the virtual test system, and comprises a scene model and a vehicle model, and is used for building a test scene, a test vehicle dynamics model and a sensor model; the data monitoring system comprises a data storage module and a data output module, monitors the data information of the vehicle in the virtual test process in real time, and displays the output data in real time in a display; the communication module is used for realizing communication connection and data transmission among the control module, the real-time dynamic module, the data monitoring system and the display; the display is used for displaying a 3D model of the virtual scene and a testing process image so as to enable a tester to observe testing conditions;
the scene model stores 3D models of six types of real dangerous traffic virtual scenes, wherein the 3D models comprise digital terrain data and traffic scene data, and a test scene can be set and comprises intersection conditions, weather conditions, illumination conditions, visual field conditions and pedestrian movement conditions;
the vehicle model comprises a dynamics model and a sensor model, wherein the dynamics model comprises a power train model, a tire model, a steering model, a vehicle body model, a suspension model, a model input and a model output, and can control signals of the speed, the direction, the position and the gesture of the vehicle; the sensor model comprises a camera, a laser radar, a millimeter wave radar and a high-precision map, the sensor is simulated to recognize and process a virtual scene, data such as the distance, the position and the angle of a vehicle and a dummy are monitored, and data information of the vehicle in the virtual test is output in real time to perform functional test.
Optionally, the control module executes a control strategy, is connected with the real-time dynamic module and the data monitoring system, is compiled by Matlab/Simulink and is imported into the control module, and sends a control signal to the real-time dynamic module to control the motion state of the vehicle.
Optionally, the real-time dynamic module is in communication connection with the data monitoring system, the real-time dynamic module sends the built vehicle model and scene model to the data monitoring system, the real-time dynamic module executes the received control signal data instruction by using the control strategy sent by the control module, modifies the vehicle dynamic model to control the motion state of the vehicle, sends the modified data to the data monitoring system again, and the data monitoring system stores, combs and outputs the received data.
Optionally, the display and the real-time dynamic module and the data monitoring system perform data transmission, and are used for displaying a 3D model of the virtual scene and a test process image, the real-time dynamic module feeds back data information of the test scene state and the test vehicle motion state to the display, the display updates the motion state of the virtual test vehicle in the scene and corresponding environmental data according to the received data information of the real-time dynamic module, and the data monitoring system sends data to be output in the test process to the display and displays the data on the display, including vehicle speed, acceleration, pedestrian speed, inter-person distance and vehicle driving distance.
Optionally, the data monitoring system comprises a data storage module and a data output module, wherein the data storage module stores all data in the virtual test process, monitors the change of each item of data in the virtual test process in real time, and records corresponding data so that test data can be derived after the test is finished; the data output module displays data to be output in the testing process to a display, wherein the data comprise vehicle speed, acceleration, pedestrian speed, inter-person distance and vehicle driving distance, and a tester performs performance test on the pedestrian automatic emergency braking system according to the speed, the acceleration and the distance displayed by the display.
Optionally, the six types of test scenes are traffic scenes in real accidents, scene analysis is performed on real accident cases which are still not avoided after 73 cases of AEB systems are additionally installed by adopting a hierarchical clustering analysis method, and typical scene features and scene elements of collision of people and vehicles in the non-avoided accidents are extracted, and the method specifically comprises the following steps:
step (1): firstly, collecting accident videos at each large video website, collecting 187 accident videos, primarily analyzing accident information in the videos, reproducing real accidents by using simulation software such as PC-crash, carsim and the like, adding an AEB control system on the basis, wherein 73 accident videos still cannot be avoided, and deeply analyzing scene information of the unavoidable accident videos;
step (II): then, carrying out feature analysis on the real traffic scene without accident, comparing scene element features, extracting 3 classes of 9 scene elements, wherein each element is represented by a value of 0, 1, 2 and the like, and the 3 classes of 9 elements are respectively:
environmental elements: lighting conditions, road characteristics, road surface conditions;
vehicle elements: vehicle speed, vehicle motion state, and view shielding condition;
pedestrian element: pedestrian speed, pedestrian motion state, pedestrian walking direction;
step (III): and performing cluster analysis on 73 cases of unavoidable accident scene information by using SPSS software by adopting a hierarchical cluster analysis method. In cluster analysis, most important is distance calculation, including inter-variable distance calculation, inter-sample distance calculation and class-to-class distance calculation;
and calculating the distance between the variables, setting the selected 9 scene elements as nominal scale variables, and obtaining the values of the 9 variables by using numerical representation of each variable. When the variable values are the same, the distance is 0, and when the variable values are different, the distance is 1, for example, in the pedestrian motion state, the characteristic values of the 'still' parameter and the 'running' parameter are respectively 0 and 2, and the distance between the variables is 1 although the difference is 2;
and calculating the distance between samples, namely calculating the distance between the samples by using Euclidean distance, and regarding n accident samples as n classes, wherein each class comprises one sample, and each sample has m sample variables. Each sample is represented by a vector containing m variables:
X i ≡(X i1 ,X i2 ,X i3 ,…,X ij ,…,X im )
wherein X is ij A metric value for a jth sample variable in the ith sample;
the distance between the i-th sample and the p-th sample is:
the computation between classes, class averaging defines the square of the distance between classes as the average of the square distances between pairs of samples,class G is generally denoted by G, assuming class G k In which there is n k Element, class G L In which there is n L The elements are of class G k And G L The square distance formula between them is as follows:
the analysis finds that 7 types of scenes are shared, but the characteristics of the motion state, the road surface condition, the view shielding condition, the road condition, the pedestrian walking direction and the like of the pedestrians in the class 4 scenes are not obvious, and the specific human-vehicle accident collision scene cannot be extracted, so that the class 4 scenes are eliminated, and the class 6 scenes are shared.
Optionally, the six types of scenes are respectively:
a first type of scenario: the speed of the vehicle is 35-55 km.h -1 Straight running, and the speed of pedestrians is 6-10 km.h -1 Running in a state, enabling pedestrians to pass through a road from the right side, drying the road surface, enabling a T-shaped intersection to enable the driver to have no shielding in view, and enabling the illumination to be good;
second class of scenes: vehicle speed>55km·h -1 Straight running, and the speed of pedestrians is 6-10 km.h -1 Running in a state that pedestrians pass through a road from the right side, the road surface is dry, the non-intersection is provided, the visual field of a driver is shielded, and the illumination is good;
third class of scenarios: the speed of the vehicle is 35-55 km.h -1 Straight running, the pedestrian speed is 0-5 km.h -1 When walking, pedestrians pass through the road from the left side, the road surface is dry, the crossroad is provided, the visual field of a driver is not blocked, and the illumination is good;
fourth class of scenes: the speed of the vehicle is 35-55 km.h -1 Straight running, the pedestrian speed is 0-5 km.h -1 When walking, pedestrians pass through the road from the right side, the road surface is wet, the road surface is not at an intersection, the driver has no shielding on the visual field, and the illumination is good;
fifth class of scenes: the speed of the vehicle is 10-35 km.h -1 Straight running, the pedestrian speed is 0-5 km.h -1 When walking, pedestrians pass through the road from the right side, the road surface is dry, the road is not at the intersection, the vision of a driver is blocked, and the illumination is good;
scene of the sixth kind: the speed of the vehicle is 10-35 km.h -1 Straight running, and the speed of pedestrians is 6-10 km.h -1 Running in a state, pedestrians pass through a road from the right side, the road surface is dry, the road is not crossed, the driver is shielded from view, and the illumination is good.
Optionally, the lighting conditions in the 3 classes of 9 scene elements comprise good, bad and poor, the road characteristics comprise crossroads, T-shaped intersections and non-intersections, the road surface conditions comprise dryness and wetness, and the vehicle speed comprises 10-35 km.h -1 、35～55km·h -1 、>55km·h -1 The vehicle motion state comprises straight running and turning, the vision shielding condition comprises shielding and no shielding, and the pedestrian speed comprises 0-5 km.h -1 、6～10km·h -1 The pedestrian motion state comprises walking and running, and the walking direction of the pedestrian comprises passing through a road from the right side and passing through the road from the left side.
Optionally, by analyzing the characteristics of the real accident traffic scene, extracting six types of human-vehicle collision typical scenes, arranging the six types of scenes into a virtual test system, and generating a virtual test case for the function of the pedestrian automatic emergency braking system.
Optionally, the virtual testing method for testing the function of the pedestrian automatic emergency braking system comprises the following steps:
s1: firstly, building a virtual test scene in a scene model, selecting a proper test scene from six types of test scenes stored in the scene model, or changing the existing virtual test scene according to test requirements;
s2: building a vehicle dynamics model in a vehicle model, selecting a virtual test vehicle type, setting an initial speed, an initial position and a motion gesture of the vehicle, selecting a sensor type in a sensor model, and setting sensor parameters;
s3: writing a control strategy of the automatic emergency braking system of the pedestrian in the Matlab/Simulink, importing the control strategy into a control module of the test system, controlling the movement of the vehicle, and continuously adjusting the control strategy and the vehicle dynamics model according to the observed movement condition of the vehicle on a display and the data information fed back by the data monitoring system so as to achieve the optimal effect of the automatic emergency braking system of the pedestrian;
s4: and finally, running a test system according to the adjusted model, and evaluating and testing the automatic emergency braking function of the pedestrians according to vehicle data, including speed, acceleration, distance between the pedestrians and the vehicles and position information, displayed on a display in real time by a tester.
The invention has the advantages that:
the virtual test system for testing the functions of the pedestrian automatic emergency braking system is characterized in that the test scene is derived from a real traffic scene, namely a domestic traffic accident case. By analyzing the characteristic elements of the traffic scene in the unavoidable accident case after the AEB system is additionally arranged, the dangerous traffic scene faced by the pedestrian automatic emergency braking system during triggering can be objectively reflected. Compared with the traditional test scene, the invention is more close to the real traffic environment, has more pertinence to the test in the dangerous scene, and the test system is a virtual test system, thereby saving manpower, financial resources and material resources, being convenient and quick, and being time-saving and efficient. The testing method is suitable for the automatic emergency braking systems of pedestrians in different technical routes, and the testing result is reliable.
Drawings
FIG. 1 is a schematic block diagram of the system of the present invention.
Detailed Description
The drawings are for illustrative purposes only and are not to be construed as limiting the present patent;
the following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Fig. 1 is a block diagram of a virtual test system for testing the function of an automatic emergency braking system for pedestrians according to an embodiment of the present invention.
As shown in fig. 1, the virtual test system for testing the pedestrian automatic emergency braking system in the embodiment of the invention comprises a control module 01, a real-time dynamic module 02, a data monitoring system 03, a communication module 04 and a display 05. The control module 01 is mainly used for inputting a control strategy, controlling a control signal of a test vehicle dynamics model according to the current system data obtained by the control strategy, and is connected with the real-time dynamic module 02 and the data monitoring system 03; the real-time dynamic module 02 provides a test platform for the virtual test system and is used for building a test scene, testing a vehicle dynamics model and a sensor model and is connected with the data monitoring system 03; the data monitoring system 03 comprises a data storage module and a data output module, monitors the data information of the vehicle in the virtual test process in real time, and displays the output data in real time in a display; the communication module 04 is used for realizing communication connection and data transmission among the control module, the real-time dynamic module, the data monitoring system and the display; the display 05 is used for displaying a 3D model of the virtual scene and a testing process image for a tester to observe testing conditions, and is connected with the real-time dynamic module 02 and the data monitoring system 03.
In one embodiment of the invention, the real-time dynamic module 02 comprises a scene model and a vehicle model, wherein the scene model stores 3D models of six types of real dangerous traffic virtual scenes, including digital terrain data and traffic scene data, and can set test scenes, including intersection conditions, weather conditions, illumination conditions, visual field conditions and pedestrian motion conditions; the vehicle model comprises a dynamics model and a sensor model, wherein the dynamics model comprises a power train model, a tire model, a steering model, a vehicle body model, a suspension model, a model input and a model output, and can control signals of the speed, the direction, the position and the gesture of the vehicle; the sensor model comprises a camera, a laser radar, a millimeter wave radar and a high-precision map, the sensor is simulated to recognize and process a virtual scene, the distance, the position and the angle between the vehicle and the dummy are monitored, and the data information of the vehicle in the virtual test is output in real time.
In one embodiment of the present invention, the data monitoring system 03 includes a data storage module and a data output module, where the data storage module stores all data in the virtual test process, monitors changes of each item of data in the virtual test process in real time, and records corresponding data; the data output module displays the data to be output in the test process to a display, wherein the data comprise vehicle speed, acceleration, pedestrian speed, inter-person distance and vehicle driving distance.
The operation of the virtual test system for testing the pedestrian automatic emergency brake system function according to the embodiment of the present invention will be described below with reference to the above-described structure.
In a specific embodiment of the present invention, a virtual test environment may be set in the real-time dynamic module, and a virtual test scene may be built in the scene model, and first, a suitable test scene is selected from six types of test scenes stored in the scene model, or an existing virtual test scene is modified according to a test requirement.
Meanwhile, a vehicle dynamics model is built in a vehicle model, wherein the vehicle dynamics model comprises a power train model, a tire model, a steering model, a vehicle body model and a suspension model, a virtual test vehicle type is selected, an initial vehicle speed, an initial position and a motion gesture are set, a sensor type is selected in a sensor model, and sensor parameters are set.
Further, a control strategy of the automatic pedestrian emergency braking system is written in Matlab/Simulink and is imported into a control module of the test system to control the movement of the vehicle, and the control strategy and the vehicle dynamics model are continuously adjusted according to the observed movement condition of the vehicle on the display and the data information fed back by the data monitoring system so as to achieve the optimal effect of the automatic pedestrian emergency braking system.
And finally, running a test system according to the adjusted model, and evaluating and testing the automatic emergency braking function of the pedestrians according to vehicle data, including speed, acceleration, distance between the pedestrians and the vehicles and position information, displayed on a display in real time by a tester.
According to the virtual test system for testing the functions of the pedestrian automatic emergency braking system, which is provided by the embodiment of the invention, the control strategy of the automatic emergency braking system is imported through the control module 01, the test platform is provided through the real-time dynamic module 02, the test scene, the test vehicle dynamics model and the sensor model are built, the data information of the vehicle in the virtual test process is monitored in real time through the data monitoring system 03, the 3D model of the virtual scene, the test process image and the data information of the test process are displayed through the display 05, and the communication connection among the modules is realized through the communication module 04, so that the characteristic information of the traffic scene in the real accident case can be effectively analyzed, the dangerous traffic scene faced by the pedestrian automatic emergency braking system when triggered is objectively reflected, the system is closer to the real traffic environment, the test under the dangerous scene is more targeted, the test system is a virtual test system, the test method is convenient, time and high efficiency are realized, the test method is suitable for the automatic pedestrian emergency braking system with different technical routes, and the test result has reliability.
The principles and embodiments of the present invention have been described with reference to specific examples, which are intended to be illustrative only of the methods and core ideas of the present invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.
Claims (8)
1. The virtual test system for testing the functions of the pedestrian automatic emergency braking system is characterized by comprising a control module, a real-time dynamic module, a data monitoring system, a communication module and a display, wherein the main functions of the modules are as follows:
the control module is mainly used for inputting a control strategy and controlling a control signal of the test vehicle dynamics model according to the current system data obtained by the control strategy; the real-time dynamic module builds a test platform for the virtual test system, and comprises a scene model and a vehicle model, wherein the scene model and the vehicle model are used for building a test scene, a test vehicle dynamics model and a sensor model; the data monitoring system comprises a data storage module and a data output module, monitors the data information of the vehicle in the virtual test process in real time, and displays the output data in real time in a display; the communication module is used for realizing communication connection and data transmission among the control module, the real-time dynamic module, the data monitoring system and the display; the display is used for displaying a 3D model of the virtual scene and a testing process image so as to enable a tester to observe testing conditions;
the scene model stores 3D models of six types of real dangerous traffic virtual scenes, wherein the 3D models comprise digital terrain data and traffic scene data, and a test scene can be set, and comprises intersection conditions, traffic conditions, weather conditions, illumination conditions, visual field conditions and pedestrian movement conditions;
the vehicle model comprises a vehicle dynamics model and a vehicle sensor model, wherein the vehicle dynamics model can control signals of vehicle speed, acceleration, direction, position and gesture, the vehicle sensor model senses surrounding environment information, and distance, position and angle data of the vehicle and surrounding objects are monitored.
2. The system of claim 1, wherein the control module is communicatively connected to the real-time dynamic module and the data monitoring system, wherein the control strategy is written by Matlab/Simulink and is imported into the control module, and the control module sends control signals to the real-time dynamic module to control the vehicle motion state.
3. The system of claim 1, wherein the real-time dynamic module is in communication connection with the data monitoring system, the real-time dynamic module transmits the built vehicle model and scene model to the data monitoring system, the real-time dynamic module executes the received control signal data command by using the control strategy transmitted by the control module, modifies the vehicle dynamics model to control the vehicle motion state, and transmits the modified data to the data monitoring system again, and the data monitoring system stores, combs and outputs the received data.
4. The system of claim 1, wherein the display performs data transmission with the real-time dynamic module and the data monitoring system, and displays the 3D model of the virtual scene and the test process image, the real-time dynamic module feeds back the built data information of the test scene state and the test vehicle motion state to the display, the display updates the motion state of the virtual test vehicle in the scene and the corresponding environmental data according to the received data information of the real-time dynamic module, and the data monitoring system sends the data to be output in the test process to the display and displays the data on the display, including the vehicle speed, the acceleration, the pedestrian speed, the inter-person distance and the vehicle driving distance.
5. The system according to claim 1, wherein the data monitoring system comprises a data storage module and a data output module, wherein the data storage module stores all data in the virtual test process, monitors the change of each item of data in the virtual test process in real time, and records corresponding data; the data output module displays the data to be output in the test process to a display, wherein the data comprise vehicle speed, acceleration, pedestrian speed, inter-person distance and vehicle driving distance.
6. The system according to claim 1, wherein the six types of test scenes in the scene model are specifically:
a first type of scenario: the speed of the vehicle is 35-55 km.h -1 Straight running, and the speed of pedestrians is 6-10 km.h -1 Running in a state, enabling pedestrians to pass through a road from the right side, drying the road surface, enabling a T-shaped intersection to enable the driver to have no shielding in view, and enabling the illumination to be good;
second class of scenes: vehicle speed>55km·h -1 Straight running, and the speed of pedestrians is 6-10 km.h -1 Running in a state that pedestrians pass through a road from the right side, the road surface is dry, the non-intersection is provided, the visual field of a driver is shielded, and the illumination is good;
third class of scenarios: the speed of the vehicle is 35-55 km.h -1 Straight running, the pedestrian speed is 0-5 km.h -1 When walking, pedestrians pass through the road from the left side, the road surface is dry, the crossroad is provided, the visual field of a driver is not blocked, and the illumination is good;
fourth class of scenes: the speed of the vehicle is 35-55 km.h -1 Straight running, the pedestrian speed is 0-5 km.h -1 When walking, pedestrians pass through the road from the right side, the road surface is wet, the road surface is not at an intersection, the driver has no shielding on the visual field, and the illumination is good;
fifth class of scenes: vehicle speed 10 to 1035km·h -1 Straight running, the pedestrian speed is 0-5 km.h -1 When walking, pedestrians pass through the road from the right side, the road surface is dry, the road is not at the intersection, the vision of a driver is blocked, and the illumination is good;
sixth category of scene: the speed of the vehicle is 10-35 km.h -1 Straight running, and the speed of pedestrians is 6-10 km.h -1 Running in a state, pedestrians pass through a road from the right side, the road surface is dry, the road is not crossed, the driver is shielded from view, and the illumination is good.
7. The system of claim 1, wherein the vehicle sensor model comprises a camera, a laser radar, a millimeter wave radar, a high precision map, and the vehicle dynamics model comprises a power train model, a tire model, a steering model, a body model, a suspension model, a model input and a model output, and outputs data information of the vehicle under virtual test in real time for functional testing.
8. The system according to claim 1, wherein the virtual test method for testing the pedestrian automatic emergency braking system function comprises the steps of:
s1: firstly, building a virtual test scene in a scene model, selecting a proper test scene from six types of test scenes stored in the scene model, or changing the existing virtual test scene according to test requirements;
s2: building a vehicle dynamics model in a vehicle model, selecting a virtual test vehicle type, setting an initial speed, an initial position and a motion gesture of the vehicle, selecting a sensor type in a sensor model, and setting sensor parameters;
s3: writing a control strategy of the automatic emergency braking system of the pedestrian in the Matlab/Simulink, importing the control strategy into a control module of the test system, controlling the movement of the vehicle, and continuously adjusting the control strategy and the vehicle model according to the observed movement condition of the vehicle on the display and the data information fed back by the data monitoring system so as to achieve the optimal effect of the automatic emergency braking system of the pedestrian;
s4: and finally, running a test system according to the adjusted model, and evaluating and testing the automatic emergency braking function of the pedestrians according to vehicle data, including speed, acceleration, distance between the pedestrians and the vehicles and position information, displayed on a display in real time by a tester.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310185678.0A CN116165915A (en) | 2023-03-01 | 2023-03-01 | Virtual test system for testing functions of pedestrian automatic emergency braking system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310185678.0A CN116165915A (en) | 2023-03-01 | 2023-03-01 | Virtual test system for testing functions of pedestrian automatic emergency braking system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116165915A true CN116165915A (en) | 2023-05-26 |
Family
ID=86418173
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310185678.0A Pending CN116165915A (en) | 2023-03-01 | 2023-03-01 | Virtual test system for testing functions of pedestrian automatic emergency braking system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116165915A (en) |
-
2023
- 2023-03-01 CN CN202310185678.0A patent/CN116165915A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3533681B1 (en) | Method for detecting safety of driving behavior, apparatus and storage medium | |
| CN111795832B (en) | Intelligent driving vehicle testing method, device and equipment | |
| CN109816811B (en) | Natural driving data acquisition device | |
| CN105892471B (en) | Automatic driving method and apparatus | |
| WO2022206942A1 (en) | Laser radar point cloud dynamic segmentation and fusion method based on driving safety risk field | |
| CN112700470B (en) | Target detection and track extraction method based on traffic video stream | |
| US20190235521A1 (en) | System and method for end-to-end autonomous vehicle validation | |
| CN111565361A (en) | Test method and test system of vehicle emergency braking early warning system based on V2V | |
| US20210171050A1 (en) | System for evaluating vehicle performance | |
| CN112116031B (en) | Target fusion method, system, vehicle and storage medium based on road side equipment | |
| CN113343461A (en) | Simulation method and device for automatic driving vehicle, electronic equipment and storage medium | |
| US20220204009A1 (en) | Simulations of sensor behavior in an autonomous vehicle | |
| CN113962011A (en) | Electric automobile braking system model and establishing method thereof | |
| Beck et al. | Automated vehicle data pipeline for accident reconstruction: New insights from LiDAR, camera, and radar data | |
| CN111845787A (en) | Lane change intention prediction method based on LSTM | |
| US11492006B2 (en) | Apparatus and methodology of road condition classification using sensor data | |
| DE112021002953T5 (en) | INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING METHOD AND PROGRAM | |
| CN113918615A (en) | Simulation-based driving experience data mining model construction method and system | |
| US11657635B2 (en) | Measuring confidence in deep neural networks | |
| CN115523934A (en) | Vehicle track prediction method and system based on deep learning | |
| Yang et al. | Driver distraction detection for vehicular monitoring | |
| CN117008574A (en) | Intelligent network allies oneself with car advanced auxiliary driving system and autopilot system test platform | |
| CN116901963A (en) | Brake control method and device for automatic driving vehicle, vehicle and medium | |
| CN116165915A (en) | Virtual test system for testing functions of pedestrian automatic emergency braking system | |
| CN114896820A (en) | Automobile train driving trafficability and performance analysis and prediction method based on virtual scene |
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 |