CN108765235A - Automatic driving vehicle test scene construction method and test method based on the destructing of traffic accident case - Google Patents
Automatic driving vehicle test scene construction method and test method based on the destructing of traffic accident case Download PDFInfo
- Publication number
- CN108765235A CN108765235A CN201810437926.5A CN201810437926A CN108765235A CN 108765235 A CN108765235 A CN 108765235A CN 201810437926 A CN201810437926 A CN 201810437926A CN 108765235 A CN108765235 A CN 108765235A
- Authority
- CN
- China
- Prior art keywords
- test
- scene
- vehicle
- automatic driving
- driving vehicle
- 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
- 238000012360 testing method Methods 0.000 title claims abstract description 274
- 206010039203 Road traffic accident Diseases 0.000 title claims abstract description 33
- 238000010276 construction Methods 0.000 title claims abstract description 12
- 238000010998 test method Methods 0.000 title claims description 15
- 238000000034 method Methods 0.000 claims abstract description 31
- 238000004458 analytical method Methods 0.000 claims abstract description 18
- 238000011156 evaluation Methods 0.000 claims abstract description 12
- 238000000605 extraction Methods 0.000 claims abstract description 6
- 238000013461 design Methods 0.000 claims description 20
- 230000006399 behavior Effects 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 7
- 230000015572 biosynthetic process Effects 0.000 claims description 6
- 230000007613 environmental effect Effects 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 5
- 239000011159 matrix material Substances 0.000 claims description 4
- 210000001520 comb Anatomy 0.000 claims description 3
- 230000001788 irregular Effects 0.000 claims description 3
- 230000003044 adaptive effect Effects 0.000 abstract description 3
- 238000011161 development Methods 0.000 abstract description 2
- 239000000284 extract Substances 0.000 abstract description 2
- 238000012252 genetic analysis Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 5
- 230000000875 corresponding effect Effects 0.000 description 4
- 238000011056 performance test Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000000556 factor analysis Methods 0.000 description 1
- 231100001261 hazardous Toxicity 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000010181 polygamy Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000004153 renaturation Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention provides a kind of automatic driving vehicle test scene construction method deconstructed based on traffic accident case, includes the following steps：（One）Pass through the signature analysis to true traffic scene, scene element of the extraction for automatic driving vehicle test；（Two）The test scene for arranging automatic driving vehicle, to generate each test case for automatic driving vehicle test；（Three）Lay test scene cooperative control system.The present invention is analyzed by way of clustering and extracts scene element and characteristic feature, in conjunction with genetic analysis, important parameter in true traffic scene is converted into test parameter, to construct a kind of method suitable for industry development and the safe adaptive testing evaluation of automatic Pilot city complexity traffic scene of Third Party Authentication evaluation.
Description
Technical field
The invention belongs to automatic driving vehicle technical field of performance test, especially a kind of to be deconstructed based on traffic accident case
Automatic driving vehicle test scene construction method and test method.
Background technology
According to automatic Pilot ability level, automatic Pilot can be mainly divided into 5 grades, and 1 grade assists to drive, and 2 grades are part
Automatic Pilot, 3 grades are automatic Pilot of having ready conditions, and 4 grades are highly automated driving, and 5 grades are fully automated driving.Wherein intelligent grade
The mankind are relied primarily on for 1 and 2 grade of automated driving system to monitor driving environment, and 3 to 5 grades of automated driving system then passes through
Computer system carries out the monitoring of driving environment.With the promotion of automatic Pilot level of intelligence, intelligence system progressivelyes reach and has
The driving ability of standby mankind driver, and after automatic Pilot level of intelligence reaches 3 to 5 grades, people will be replaced in part scene
Class completes driving task.
Currently deepen continuously to Function for Automatic Pilot research with domestic and international research institution, the intelligence of automatic driving vehicle
Horizontal gradually realize promotes from auxiliary driving to unmanned direction.For ensure the operational safety of different brackets intelligence system with it is steady
It is qualitative, it needs to carry out test certification to the basic security performance of automated driving system, and drive automatically to verify according to test result
Sail the safety in operation of vehicle.
Automatic driving vehicle may be implemented certainly by the coordinated of the systems such as perception, decision and control, execution at this stage
It is dynamic to drive operation function.And it is gradually complete for the test of the basic functions such as the emergency braking of automatic Pilot, adaptive cruise
It is kind, but hardware performance test of such test method mostly based on automatic driving vehicle, automatic Pilot survey can not be reacted well
Logic adaptability of the amount in face of complicated traffic environment；Therefore, it is necessary to construct a kind of to react China's typical road traffic environment
In dangerous scene, cover relatively conventional accident and illegal scene, standardization can concentrated expression automatic driving vehicle pass through ring
The test scene of border adaptability.
Invention content
It is an object of the present invention to overcome the shortcomings of the prior art and provide one kind to be deconstructed based on traffic accident case
Automatic driving vehicle test scene construction method and corresponding test method, refinement is analyzed by way of clustering
Go out scene element and characteristic feature, in conjunction with genetic analysis, the important parameter in true traffic scene is converted into test parameter, from
And construct a kind of automatic Pilot city complexity traffic scene adaptation safely suitable for industry development and Third Party Authentication evaluation
The method of property test evaluation.The technical solution adopted by the present invention is：
A kind of automatic driving vehicle test scene construction method based on the destructing of traffic accident case, includes the following steps：
(1) pass through the signature analysis to true traffic scene, scene element of the extraction for automatic driving vehicle test；
(2) test scene for arranging automatic driving vehicle, generates each test case for automatic driving vehicle test；
(3) test scene cooperative control system is laid.
Specifically, in step (1), signature analysis is based on traffic accident case；Analytical procedure includes data prediction, answers
Polygamy analysis, scene element aspect ratio pair；
Step 1.1, data prediction：Classify for scene element, in conjunction with the traveling behavior of real vehicles, to each friendship
Logical accident case forms case list；
Step 1.2, the complexity analyzing of traffic accident case：The phase for the traffic accident case after data prediction of learning from else's experience
Character matrix is closed, the complexity of case is calculated；
Step 1.3, scene element aspect ratio pair：By carrying out across comparison analysis to each traffic accident case, take
The relevance between each scene is sought with the method for mathematical statistics, and symbolizes the characteristic feature of dangerous scene, combs out danger
With common scene element.
Further, in step 1.1, the classification of scene element includes：The accident origin cause of formation, accident object, incident area, environment
Condition；The behavior that wherein the accident origin cause of formation is expressed as the reference vehicle chosen includes irregular driving, tired driving, new hand's driving；Thing
Therefore object includes other vehicles, non-motor vehicle, pedestrian；Incident area includes straight trip section, intersection, main and side road, entrance, soon
Fast road, crossing region, platform region；Environmental condition includes rainy day, greasy weather, night, ice and snow, dusk；The row of real vehicles
The behavior of sailing includes：With speeding, turning, avoid, lane change, overtake other vehicles, flow back.
Specifically, in step (2), test scene includes：Test vehicle, test road, test facilities, testing background object.
Specifically, in test scene cooperative control system, test vehicle is equipped with according to testing requirement for determining test
The mobile satellite location equipment of location information, running velocity, course angle essential information, test vehicle will be tested by wireless network
The essential information of vehicle is transmitted to Background control terminal server；Background control terminal server is according to the test vehicle received
Essential information presets the state trigger timing of node timely adjustment test facilities and testing background object in conjunction with scene.
A kind of test method, in the above-mentioned automatic driving vehicle test scene structure side based on the destructing of traffic accident case
On the basis of method, including test assignment complexity design method, test assignment form module design method, test evaluation side
Method.
Specifically, test assignment complexity design method includes：With reference first to the signature analysis of true traffic scene, will survey
Examination element is added in test scene to generate the automatic driving vehicle test case of differing complexity；
These test elements include the scene element for automatic driving vehicle test extracted in step (1), and are surveyed
Test vehicle, test facilities, testing background object when examination hall scape is laid.
Further, by adding the identification of various dimensions of test vehicle, decision, executive subsystem in test scene
Test elements, to realize the promotion of test scene complexity.
Specifically, test assignment form module design method includes：Test assignment is showed with task form；
Pilot point in task form indicates the process of test assignment；Each pilot point includes several attribute points；Pilot point
Data type include each attribute point three-dimensional coordinate, both longitude, latitude, height；
Each attribute point represents the path point for guiding test vehicle pass-through of testing agency's offer；
Complexity in task form is coupled by the selection quantity and test elements of test elements in test scene
The annoyance level of test is determined afterwards.
Specifically, test evaluation method specifically includes：
Under the conditions of same test complexity, the pilot point of corresponding demand is provided according to different test vehicle design requirements
Attribute point quantity, the safe passing ability of intelligent level and unknown scene for evaluating different test vehicles；
Under the conditions of same test complexity, by constantly reducing the attribute point quantity of pilot point, for evaluating same survey
Test run adapts to the limiting condition of test scene；
Under the conditions of identical pilot point and attribute point, the energy of test environment adaptability is faced for evaluating different test vehicles
Power；
The abundant test content of vertex type is guided by variation, guides vertex type to obtain a variety of test zones by variation, and
Carry out the traffic capacity test case that vehicle is tested in these test zones.
The advantage of the invention is that：
The automatic driving vehicle test scene of the present invention derives from true traffic scene, i.e. domestic communication accident case.It is logical
The factor analysis to true traffic scene is crossed, the danger that automatic driving vehicle is faced when real roads are passed through can be objectively responded out
Dangerous traffic scene.The setting method of this test scene is by the way of the dangerous true traffic scene of reproduction, with traditional test scene
Setting compare, the present invention is tested not only for realizing that the limiting condition of hardware device of automatic function is tested
Core be this method can be used for Comprehensive Assessment automated driving system operation logic whether adapt to China road traffic it is logical
Row condition.
The present invention coordinates checkout area in the setting and test approach of test case using true closed field test
Scape cooperative control system carries out, and the test vehicle in can test being started, be tested detects in real time, and according to the operation of test vehicle
State adjusts the running position of background equipment, it is ensured that the concertedness of test vehicle and background equipment ensures the normal of test case
Carry out.Scene using reproduction by the way of, for restore automatic driving vehicle run in real roads can face have generation
The dangerous traffic scene of traffic accident possibility, and the scene is arranged based on objective angle so that this test method is suitable for not
With the automatic driving vehicle of technology path, standardization third party tests with exploitation, and test result has reliability.The survey of the present invention
Method for testing compared with hardware-in―the-loop test, computer simulation emulation scheduling theory data test, closer to true traffic pass through ring
Border, test dimension and can be reflected objectively between each system of automatic driving vehicle not only for the basic performance of system
Coordinated ability so that test result more can accurately graticule test vehicle integrated operation security performance.With real roads
Test is compared, this test method carries out test job using closing place, safe emergency response mechanism is provided with, compared to true
Road test is more safely controllable, and can avoid the randomness of road test, and can carry out weight to the dangerous scene that need to repeat examination
Renaturation verification test.
Description of the drawings
Fig. 1 is the test scene arrangement figure of the present invention.
Fig. 2 is the test scene cooperative control system schematic diagram of the present invention.
Specific implementation mode
With reference to specific drawings and examples, the invention will be further described.
Automatic driving vehicle test scene construction method and test proposed by the present invention based on the destructing of traffic accident case
Method, including：
(1) pass through the signature analysis to true traffic scene, scene element of the extraction for automatic driving vehicle test；
Signature analysis is based on traffic accident case, and case type includes folder, video etc.；Analytical procedure includes that data are located in advance
Reason, complexity analyzing, scene element aspect ratio pair；
Step 1.1, data prediction：Classify for scene element, in conjunction with the traveling behavior of real vehicles, to each friendship
Logical accident case forms case list；As shown in table 1；
The classification of scene element includes：The accident origin cause of formation, accident object, incident area, environmental condition；Wherein accident origin cause of formation table
The behavior for being shown as the reference vehicle chosen includes irregular driving, tired driving, new hand's driving etc.；Accident object includes other vehicles
, non-motor vehicle, pedestrian；Incident area includes straight trip section, intersection, main and side road, entrance, through street, crossing area
Domain, platform region；Environmental condition includes rainy day, greasy weather, night, ice and snow, dusk；The traveling behavior of real vehicles includes：With speeding,
Turning, lane change, overtakes other vehicles, flows back at evacuation；
1 case list of table
Each traffic accident case forms a case list as shown in Table 1；Each traffic accident case representation is
Character matrix (aij)n×m；aijFor the value of cell in case list, take " 0 represent it is non-, 1 represent be " expression-form；n
Indicate that line number, m indicate columns；
Step 1.2, the complexity analyzing of traffic accident case：The phase for the traffic accident case after data prediction of learning from else's experience
Character matrix is closed, the complexity of case is set as γ, is expressed as：
The numerical values recited showed by γ can obtain the quantity of the influence factor in the traffic accident case, can be used for point
Analyse the complexity of traffic accident；If there is the number in seven cells to be in the corresponding case list of a traffic accident case
1, illustrate that the traffic accident case there are 7 influence factors；
Step 1.3, scene element aspect ratio pair：By carrying out across comparison analysis to each traffic accident case, take
The relevance between each scene is sought with the method for mathematical statistics, and symbolizes the characteristic feature of dangerous scene, combs out danger
With common scene element；
It specifically can be using the higher element parameter of occurrence probability in table 1 as dangerous and common scene element；Such as it endangers
The road segment classification of danger, hazardous environment condition, common road traffic law violation behavior etc.；
Test parameters of the danger and common scene element of these extractions in being test scene in subsequent conversion；
(2) test scene for arranging automatic driving vehicle is used to generate for each test of automatic driving vehicle test
Example；As shown in Figure 1；
Test scene includes：Test vehicle, test road, test facilities, testing background object；
The basic parameter, including initial velocity, traffic direction etc. of setting test vehicle；
It includes linear road, bend, intersection, main and side road etc. to test road；
Test facilities include sign board, graticule, signal lamp etc.；
Testing background object includes background dummy, background non-motor vehicle, background vehicle etc.；
Test scene can carry out the reproduction of true traffic scene when automatic driving vehicle is tested；
Each test case of automatic driving vehicle test is built in test scene, including：Avoid the non-machine of reverse driving
Non-maneuver garage is followed in motor-car, night avoid the non-motor vehicle jaywalked, evacuation is made a dash across the red light current non-motor vehicle, narrow road
It sails, surmount the non-motor vehicle that front travels at a slow speed, identification front vehicles emergency braking, the bus station by there is Public Transit Bus Stopping
Deng；
(3) test scene cooperative control system is laid；As shown in Figure 2；
To realize the orderly function of above-mentioned test scene, standardizing, accurately for automatic driving vehicle environmental suitability is realized
Change test, the present invention is provided with a kind of test scene cooperative control system；
In test scene cooperative control system, test vehicle is equipped with according to testing requirement for determining that test position is believed
The mobile satellite location equipment of the essential informations such as breath, running velocity, course angle, test vehicle will test vehicle by wireless network
Essential information be transmitted to Background control terminal server；Background control terminal server is basic according to the test vehicle received
Information presets the state trigger timing of node timely adjustment test facilities and testing background object in conjunction with scene, to ensure checkout area
Scape can refine reproduction test design requirement, ensure the standardization of test process；
(4) test method includes test assignment complexity design method, test assignment form module design method, surveys
Try evaluation method；
The purpose of structure test method is in order to establish standardization, modular test content, by different test sample vehicles
Testing process it is unitized, and the test process of specification automatic driving vehicle, it is ensured that test process meets the phase of test foundation
It closes and requires；
4.1) test assignment complexity design method；
With reference first to the signature analysis of true traffic scene, test elements are added in test scene different multiple to generate
The automatic driving vehicle test case of miscellaneous degree；
These test elements include the scene element for automatic driving vehicle test extracted in step (1), and are surveyed
Test vehicle, test facilities, testing background object when examination hall scape is laid；
Further, by adding the identification of various dimensions of test vehicle, decision, executive subsystem in test scene
Test elements, to realize the promotion of test scene complexity, to realize the automatic Pilot test carriage to different intelligent grade
Proficiency testing testing requirement；
Table 2 is participated in the design of test assignment complexity list；
Table 2
| Complexity | Element 1 | Element 2 | … |
| Element 1 | |||
| Element 2 | |||
| … | … |
4.2) test assignment form module design method；
Test assignment form moduleization designs, main to consider automatic driving vehicle actual test in the way of sub-module
It carries out；The ability that automatic driving vehicle can be examined to complete modules task during test respectively, and conveniently to each
Module is tested；
Test assignment is showed with task form；Task form participates in following Table 3；
Table 3
| Guide vertex type | Attribute point 1 | Attribute point 2 | Attribute point 3 | ....... | Attribute point n | Complexity |
| 1 | ||||||
| 2 |
Pilot point in task form indicates the process of test assignment；The data type of pilot point includes the three of each attribute point
WGS84 coordinates are tieed up, both longitude, latitude, height；
Each pilot point includes several attribute points, and each attribute point represents the logical for guiding test vehicle of testing agency's offer
Capable path point；If it is simpler that the pilot point provided and the number of attribute point more at most represent test being executed for task of vehicle
It is single；By increasing attribute point quantity, the design of the traffic element in expression a road section is realized, for example, pilot point 1 can be used for table
Show that test assignment 1, such as 1 value of attribute point represent starting point for 0, attribute point 2 takes 1 to represent intersection access point, and attribute point 3 took for 2 generations
Table intersection goes out a little, and attribute point 4 takes 3 to represent terminal；
Complexity in task form is coupled by the selection quantity and test elements of test elements in test scene
The annoyance level of test is determined afterwards.
4.3) test evaluation method；
Guiding point design in the complexity and task form of test evaluation binding test task；Test elements integrated level with
The sparse degree of task will influence the test complexity of automatic driving vehicle, and the complexity of test assignment and attribute point
Sparse degree presents negatively correlated；
Under the conditions of same test complexity, the pilot point of corresponding demand is provided according to different test vehicle design requirements
Attribute point quantity, the safe passing ability of intelligent level and unknown scene for evaluating different test vehicles；
Under the conditions of same test complexity, by constantly reducing the attribute point quantity of pilot point, for evaluating same survey
Test run adapts to the limiting condition of test scene；
Under the conditions of identical pilot point and attribute point, the energy of test environment adaptability is faced for evaluating different test vehicles
Power；
The abundant test content of vertex type is guided by changing, such as can be kept straight on by variation guiding vertex type, is right
Turn through intersection, turn left through a variety of test zones such as intersection, U-shaped turning, parkings, and carries out and surveyed in these test zones
The traffic capacity test case of test run；
To sum up, the present invention is in the preparation stage of test, according to the safe adaptive testing demand of automatic driving vehicle, parameter
Change true traffic scene, and extracts scene element and form test elements.The test arrangement stage, according to true after former data processing
Real traffic scene arranges test scene and test scene cooperative control system in closed test place, and with reference to test parameters
Tested tissue vehicle carries out test preparation.It tests the incipient stage, performance test scene cooperative control system, according to test vehicle institute
The essential information of feedback completes the coordinated of test facilities and testing background object, ensures that the standardization of test is run, and according to
The coordinated ability integration evaluation of the ability and each subsystem of automatic driving vehicle of testing vehicle completion test scene is automatic
Drive the safe and applicable sexuality of vehicle.
Claims (10)
1. a kind of automatic driving vehicle test scene construction method based on the destructing of traffic accident case, which is characterized in that including
Following steps：
（One）Pass through the signature analysis to true traffic scene, scene element of the extraction for automatic driving vehicle test；
（Two）It arranges the test scene of automatic driving vehicle, generates each test case for automatic driving vehicle test；
（Three）Lay test scene cooperative control system.
2. the automatic driving vehicle test scene construction method as described in claim 1 based on the destructing of traffic accident case,
It is characterized in that,
Step（One）In, signature analysis is based on traffic accident case；Analytical procedure includes data prediction, complexity analyzing, field
Scape element characteristic compares；
Step 1.1, data prediction：Classify for scene element, in conjunction with the traveling behavior of real vehicles, to each traffic thing
Therefore case forms case list；
Step 1.2, the complexity analyzing of traffic accident case：The dependency number for the traffic accident case after data prediction of learning from else's experience
Word matrix calculates the complexity of case；
Step 1.3, scene element aspect ratio pair：By carrying out across comparison analysis to each traffic accident case, utilization is taken
The method of mathematical statistics seeks the relevance between each scene, and symbolizes the characteristic feature of dangerous scene, combs out dangerous and normal
The scene element seen.
3. the automatic driving vehicle test scene construction method as claimed in claim 2 based on the destructing of traffic accident case,
It is characterized in that,
In step 1.1, the classification of scene element includes：The accident origin cause of formation, accident object, incident area, environmental condition；Wherein accident
The behavior that the origin cause of formation is expressed as the reference vehicle chosen includes irregular driving, tired driving, new hand's driving；Accident object includes other
Vehicle, non-motor vehicle, pedestrian；Incident area includes straight trip section, intersection, main and side road, entrance, through street, crossing
Region, platform region；Environmental condition includes rainy day, greasy weather, night, ice and snow, dusk；The traveling behavior of real vehicles includes：With
It speeds, turn, avoiding, lane change, overtake other vehicles, flow back.
4. the automatic driving vehicle test scene construction method as described in claim 1 based on the destructing of traffic accident case,
It is characterized in that,
Step（Two）In, test scene includes：Test vehicle, test road, test facilities, testing background object.
5. the automatic driving vehicle test scene construction method as claimed in claim 4 based on the destructing of traffic accident case,
It is characterized in that,
In test scene cooperative control system, test vehicle is equipped with according to testing requirement for determining test position information, vehicle
The speed of service, the mobile satellite location equipment of course angle essential information, test vehicle will test the basic of vehicle by wireless network
Information is transmitted to Background control terminal server；The test vehicle essential information that Background control terminal server foundation receives,
The state trigger timing of node timely adjustment test facilities and testing background object is preset in conjunction with scene.
6. a kind of test method, in the automatic Pilot according to any one of claims 1 to 5 based on the destructing of traffic accident case
On the basis of vehicle testing scenario building method, which is characterized in that
Including test assignment complexity design method, test assignment form module design method, test evaluation method.
7. test method as claimed in claim 6, which is characterized in that
Test assignment complexity design method includes：With reference first to the signature analysis of true traffic scene, test elements are added
To generate the automatic driving vehicle test case of differing complexity in test scene；
These test elements include step（One）The scene element and checkout area for automatic driving vehicle test of middle extraction
Test vehicle, test facilities, testing background object when scape is laid.
8. test method as claimed in claim 7, which is characterized in that
By the identification of the various dimensions of addition test vehicle, decision, the test elements of executive subsystem in test scene, come real
The promotion of existing test scene complexity.
9. test method as claimed in claim 6, which is characterized in that
Test assignment form module design method includes：Test assignment is showed with task form；
Pilot point in task form indicates the process of test assignment；Each pilot point includes several attribute points；The number of pilot point
Include the three-dimensional coordinate of each attribute point according to type, both longitude, latitude, height；
Each attribute point represents the path point for guiding test vehicle pass-through of testing agency's offer；
Complexity in task form is right after being coupled by the selection quantity and test elements of test elements in test scene
The annoyance level of test determines.
10. test method as claimed in claim 6, which is characterized in that
Test evaluation method specifically includes：
Under the conditions of same test complexity, the attribute of the pilot point of corresponding demand is provided according to different test vehicle design requirements
Point quantity, the safe passing ability of intelligent level and unknown scene for evaluating different test vehicles；
Under the conditions of same test complexity, by constantly reducing the attribute point quantity of pilot point, for evaluating same test carriage
Adapt to test scene limiting condition；
Under the conditions of identical pilot point and attribute point, the ability for evaluating different test vehicles in face of test environment adaptability；
The abundant test content of vertex type is guided by variation, guides vertex type to obtain a variety of test zones by variation, and carry out
The traffic capacity test case of vehicle is tested in these test zones.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810437926.5A CN108765235A (en) | 2018-05-09 | 2018-05-09 | Automatic driving vehicle test scene construction method and test method based on the destructing of traffic accident case |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810437926.5A CN108765235A (en) | 2018-05-09 | 2018-05-09 | Automatic driving vehicle test scene construction method and test method based on the destructing of traffic accident case |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108765235A true CN108765235A (en) | 2018-11-06 |
Family
ID=64009688
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810437926.5A Pending CN108765235A (en) | 2018-05-09 | 2018-05-09 | Automatic driving vehicle test scene construction method and test method based on the destructing of traffic accident case |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108765235A (en) |
Cited By (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109753623A (en) * | 2018-12-10 | 2019-05-14 | 清华大学 | A kind of analysis of automatic driving vehicle multi-test scene and number simplifying method |
| CN109900494A (en) * | 2019-02-25 | 2019-06-18 | 上海机动车检测认证技术研究中心有限公司 | A kind of generation method of test case |
| CN109948217A (en) * | 2019-03-12 | 2019-06-28 | 中国汽车工程研究院股份有限公司 | A kind of dangerous scene base construction method based on natural driving data |
| CN109993849A (en) * | 2019-03-22 | 2019-07-09 | 山东省科学院自动化研究所 | A kind of automatic Pilot test scene render analog method, apparatus and system |
| CN110553853A (en) * | 2019-08-06 | 2019-12-10 | 清华大学 | automatic driving function test and evaluation method based on poor scene search under field |
| CN110597711A (en) * | 2019-08-26 | 2019-12-20 | 湖南大学 | Automatic driving test case generation method based on scene and task |
| CN110606093A (en) * | 2019-09-26 | 2019-12-24 | 中国第一汽车股份有限公司 | Vehicle performance evaluation method, device, equipment and storage medium |
| CN110686906A (en) * | 2019-10-09 | 2020-01-14 | 清华大学 | Automatic driving test method and device for vehicle |
| CN110688311A (en) * | 2019-09-25 | 2020-01-14 | 武汉光庭信息技术股份有限公司 | Test case management method and device for automatic driving typical scene |
| CN110705134A (en) * | 2019-12-13 | 2020-01-17 | 中智行科技有限公司 | Driving test method, device, equipment and computer readable storage medium |
| CN110716529A (en) * | 2019-09-25 | 2020-01-21 | 武汉光庭信息技术股份有限公司 | Automatic generation method and device for automatic driving test case |
| CN110782125A (en) * | 2019-09-23 | 2020-02-11 | 同济大学 | Road safety risk degree evaluation method for automatically driving automobile |
| CN110955159A (en) * | 2019-11-28 | 2020-04-03 | 安徽江淮汽车集团股份有限公司 | Automatic driving simulation example compiling method and device, electronic equipment and storage medium |
| CN111179585A (en) * | 2018-11-09 | 2020-05-19 | 上海汽车集团股份有限公司 | Site testing method and device for automatic driving vehicle |
| CN111178402A (en) * | 2019-12-13 | 2020-05-19 | 赛迪检测认证中心有限公司 | Scene classification method and device for road test of automatic driving vehicle |
| CN111426486A (en) * | 2020-03-30 | 2020-07-17 | 中国标准化研究院 | Test method, device and equipment of driving assistance system and storage medium |
| CN111539087A (en) * | 2019-01-18 | 2020-08-14 | 上汽通用汽车有限公司 | Automatic driving system simulation test platform and automatic driving system evaluation method |
| CN111651712A (en) * | 2020-05-27 | 2020-09-11 | 北京航空航天大学 | Method and system for evaluating complexity of test scene of intelligent automobile |
| CN111666307A (en) * | 2019-12-03 | 2020-09-15 | 张少军 | Unmanned safety judgment system for intuitive inference according to scene observation |
| CN112665875A (en) * | 2020-12-25 | 2021-04-16 | 北京智能车联产业创新中心有限公司 | Method and device for testing reliability of automatic driving vehicle, electronic equipment and storage medium |
| CN112835790A (en) * | 2021-01-22 | 2021-05-25 | 北京罗克维尔斯科技有限公司 | Test method, device, equipment and medium for automatic driving software |
| CN112947080A (en) * | 2021-02-04 | 2021-06-11 | 中国运载火箭技术研究院 | Scene parameter transformation-based intelligent decision model performance evaluation system |
| CN113095276A (en) * | 2021-04-26 | 2021-07-09 | 中国汽车工程研究院股份有限公司 | Method for measuring data complexity of automobile image scene library |
| CN113272744A (en) * | 2019-12-17 | 2021-08-17 | 弗泰里克斯有限公司 | System for monitoring appropriate behavior of autonomous vehicle and method thereof |
| CN114003582A (en) * | 2021-10-26 | 2022-02-01 | 同济大学 | Traffic accident foreground derivation method for automatic driving vehicle and storage medium |
| CN115240409A (en) * | 2022-06-17 | 2022-10-25 | 上海智能网联汽车技术中心有限公司 | Method for extracting dangerous scene based on driver model and traffic flow model |
| US11644331B2 (en) | 2020-02-28 | 2023-05-09 | International Business Machines Corporation | Probe data generating system for simulator |
| US11702101B2 (en) | 2020-02-28 | 2023-07-18 | International Business Machines Corporation | Automatic scenario generator using a computer for autonomous driving |
| CN116778720A (en) * | 2023-08-25 | 2023-09-19 | 中汽传媒(天津)有限公司 | Traffic condition scene library construction and application method, system and electronic equipment |
| CN116881778A (en) * | 2023-09-06 | 2023-10-13 | 交通运输部公路科学研究所 | Intelligent auxiliary teaching system safety early warning and protection function testing system and method |
| US11814080B2 (en) | 2020-02-28 | 2023-11-14 | International Business Machines Corporation | Autonomous driving evaluation using data analysis |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103207090A (en) * | 2013-04-09 | 2013-07-17 | 北京理工大学 | Driverless vehicle environment simulation test system and test method |
| CN103234763A (en) * | 2013-04-09 | 2013-08-07 | 北京理工大学 | System and method for quantitatively evaluating unmanned vehicles |
| CN105956268A (en) * | 2016-04-29 | 2016-09-21 | 百度在线网络技术（北京）有限公司 | Construction method and device applied to test scene of pilotless automobile |
-
2018
- 2018-05-09 CN CN201810437926.5A patent/CN108765235A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103207090A (en) * | 2013-04-09 | 2013-07-17 | 北京理工大学 | Driverless vehicle environment simulation test system and test method |
| CN103234763A (en) * | 2013-04-09 | 2013-08-07 | 北京理工大学 | System and method for quantitatively evaluating unmanned vehicles |
| CN105956268A (en) * | 2016-04-29 | 2016-09-21 | 百度在线网络技术（北京）有限公司 | Construction method and device applied to test scene of pilotless automobile |
Cited By (47)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111179585A (en) * | 2018-11-09 | 2020-05-19 | 上海汽车集团股份有限公司 | Site testing method and device for automatic driving vehicle |
| CN109753623B (en) * | 2018-12-10 | 2020-05-01 | 清华大学 | Method for analyzing multiple test scenes and simplifying number of automatic driving vehicles |
| CN109753623A (en) * | 2018-12-10 | 2019-05-14 | 清华大学 | A kind of analysis of automatic driving vehicle multi-test scene and number simplifying method |
| CN111539087B (en) * | 2019-01-18 | 2024-04-09 | 上汽通用汽车有限公司 | Automatic driving system simulation test platform and automatic driving system evaluation method |
| CN111539087A (en) * | 2019-01-18 | 2020-08-14 | 上汽通用汽车有限公司 | Automatic driving system simulation test platform and automatic driving system evaluation method |
| CN109900494B (en) * | 2019-02-25 | 2021-04-13 | 上海机动车检测认证技术研究中心有限公司 | Test case generation method |
| CN109900494A (en) * | 2019-02-25 | 2019-06-18 | 上海机动车检测认证技术研究中心有限公司 | A kind of generation method of test case |
| CN109948217A (en) * | 2019-03-12 | 2019-06-28 | 中国汽车工程研究院股份有限公司 | A kind of dangerous scene base construction method based on natural driving data |
| CN109993849A (en) * | 2019-03-22 | 2019-07-09 | 山东省科学院自动化研究所 | A kind of automatic Pilot test scene render analog method, apparatus and system |
| CN110553853B (en) * | 2019-08-06 | 2020-11-20 | 清华大学 | Automatic driving function test and evaluation method based on poor scene search under field |
| CN110553853A (en) * | 2019-08-06 | 2019-12-10 | 清华大学 | automatic driving function test and evaluation method based on poor scene search under field |
| CN110597711B (en) * | 2019-08-26 | 2023-02-10 | 湖南大学 | Automatic driving test case generation method based on scene and task |
| CN110597711A (en) * | 2019-08-26 | 2019-12-20 | 湖南大学 | Automatic driving test case generation method based on scene and task |
| CN110782125A (en) * | 2019-09-23 | 2020-02-11 | 同济大学 | Road safety risk degree evaluation method for automatically driving automobile |
| CN110782125B (en) * | 2019-09-23 | 2023-05-02 | 同济大学 | Road safety risk assessment method for automatic driving automobile |
| CN110716529A (en) * | 2019-09-25 | 2020-01-21 | 武汉光庭信息技术股份有限公司 | Automatic generation method and device for automatic driving test case |
| CN110688311A (en) * | 2019-09-25 | 2020-01-14 | 武汉光庭信息技术股份有限公司 | Test case management method and device for automatic driving typical scene |
| CN110606093A (en) * | 2019-09-26 | 2019-12-24 | 中国第一汽车股份有限公司 | Vehicle performance evaluation method, device, equipment and storage medium |
| CN110686906B (en) * | 2019-10-09 | 2021-03-26 | 清华大学 | Automatic driving test method and device for vehicle |
| CN110686906A (en) * | 2019-10-09 | 2020-01-14 | 清华大学 | Automatic driving test method and device for vehicle |
| CN110955159A (en) * | 2019-11-28 | 2020-04-03 | 安徽江淮汽车集团股份有限公司 | Automatic driving simulation example compiling method and device, electronic equipment and storage medium |
| CN110955159B (en) * | 2019-11-28 | 2021-05-11 | 安徽江淮汽车集团股份有限公司 | Automatic driving simulation example compiling method and device, electronic equipment and storage medium |
| CN111666307A (en) * | 2019-12-03 | 2020-09-15 | 张少军 | Unmanned safety judgment system for intuitive inference according to scene observation |
| CN110705134A (en) * | 2019-12-13 | 2020-01-17 | 中智行科技有限公司 | Driving test method, device, equipment and computer readable storage medium |
| CN111178402A (en) * | 2019-12-13 | 2020-05-19 | 赛迪检测认证中心有限公司 | Scene classification method and device for road test of automatic driving vehicle |
| CN111178402B (en) * | 2019-12-13 | 2023-04-07 | 赛迪检测认证中心有限公司 | Scene classification method and device for road test of automatic driving vehicle |
| CN113272744A (en) * | 2019-12-17 | 2021-08-17 | 弗泰里克斯有限公司 | System for monitoring appropriate behavior of autonomous vehicle and method thereof |
| US11702101B2 (en) | 2020-02-28 | 2023-07-18 | International Business Machines Corporation | Automatic scenario generator using a computer for autonomous driving |
| US11814080B2 (en) | 2020-02-28 | 2023-11-14 | International Business Machines Corporation | Autonomous driving evaluation using data analysis |
| US11644331B2 (en) | 2020-02-28 | 2023-05-09 | International Business Machines Corporation | Probe data generating system for simulator |
| CN111426486B (en) * | 2020-03-30 | 2022-01-21 | 中国标准化研究院 | Test method, device and equipment of driving assistance system and storage medium |
| CN111426486A (en) * | 2020-03-30 | 2020-07-17 | 中国标准化研究院 | Test method, device and equipment of driving assistance system and storage medium |
| CN111651712A (en) * | 2020-05-27 | 2020-09-11 | 北京航空航天大学 | Method and system for evaluating complexity of test scene of intelligent automobile |
| CN111651712B (en) * | 2020-05-27 | 2023-03-28 | 北京航空航天大学 | Method and system for evaluating complexity of test scene of intelligent automobile |
| CN112665875A (en) * | 2020-12-25 | 2021-04-16 | 北京智能车联产业创新中心有限公司 | Method and device for testing reliability of automatic driving vehicle, electronic equipment and storage medium |
| CN112835790A (en) * | 2021-01-22 | 2021-05-25 | 北京罗克维尔斯科技有限公司 | Test method, device, equipment and medium for automatic driving software |
| CN112947080A (en) * | 2021-02-04 | 2021-06-11 | 中国运载火箭技术研究院 | Scene parameter transformation-based intelligent decision model performance evaluation system |
| CN112947080B (en) * | 2021-02-04 | 2023-04-14 | 中国运载火箭技术研究院 | Scene parameter transformation-based intelligent decision model performance evaluation system |
| CN113095276A (en) * | 2021-04-26 | 2021-07-09 | 中国汽车工程研究院股份有限公司 | Method for measuring data complexity of automobile image scene library |
| CN114003582A (en) * | 2021-10-26 | 2022-02-01 | 同济大学 | Traffic accident foreground derivation method for automatic driving vehicle and storage medium |
| CN114003582B (en) * | 2021-10-26 | 2024-09-06 | 同济大学 | Traffic accident scene derivation method for automatic driving vehicle and storage medium |
| CN115240409A (en) * | 2022-06-17 | 2022-10-25 | 上海智能网联汽车技术中心有限公司 | Method for extracting dangerous scene based on driver model and traffic flow model |
| CN115240409B (en) * | 2022-06-17 | 2024-02-06 | 上智联(上海)智能科技有限公司 | Method for extracting dangerous scene based on driver model and traffic flow model |
| CN116778720A (en) * | 2023-08-25 | 2023-09-19 | 中汽传媒(天津)有限公司 | Traffic condition scene library construction and application method, system and electronic equipment |
| CN116778720B (en) * | 2023-08-25 | 2023-11-24 | 中汽传媒(天津)有限公司 | Traffic condition scene library construction and application method, system and electronic equipment |
| CN116881778A (en) * | 2023-09-06 | 2023-10-13 | 交通运输部公路科学研究所 | Intelligent auxiliary teaching system safety early warning and protection function testing system and method |
| CN116881778B (en) * | 2023-09-06 | 2023-11-28 | 交通运输部公路科学研究所 | Intelligent auxiliary teaching system safety early warning and protection function testing system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108765235A (en) | Automatic driving vehicle test scene construction method and test method based on the destructing of traffic accident case | |
| EP3533681B1 (en) | Method for detecting safety of driving behavior, apparatus and storage medium | |
| Chen et al. | Analysis of factors affecting the severity of automated vehicle crashes using XGBoost model combining POI data | |
| CN102819954B (en) | Traffic region dynamic map monitoring and predicating system | |
| CN110716529A (en) | Automatic generation method and device for automatic driving test case | |
| Pi et al. | Automotive platoon energy-saving: A review | |
| CN107395757B (en) | Parallel vehicle networking system based on ACP method and social physical information system | |
| Lee et al. | Indicators development to support intelligent road infrastructure in urban cities | |
| CN112907955A (en) | Evaluation method of vehicle-road cooperative system based on information fusion | |
| Ma et al. | Developing a safety heatmap of uncontrolled intersections using both conflict probability and severity | |
| Branzi et al. | A Combined Simulation Approach to Evaluate Overtaking Behaviour on Two‐Lane Two‐Way Rural Roads | |
| He et al. | Analysis of urban traffic accidents features and correlation with traffic congestion in large-scale construction district | |
| Lu et al. | Research on the intelligent assignment model of urban traffic planning based on optimal path optimization algorithm | |
| Barabino et al. | Refining a crash risk framework for urban bus safety assessment: Evidence from Sardinia (Italy) | |
| Wang | Real‐Time Evaluation Method of Vehicle Conflict Risk on Urban Expressway Based on Smartphone GPS Data | |
| Xu et al. | Novel fast safety assessment method for the buffer section of maintenance work zone | |
| CN109686099A (en) | A kind of bus zone illegal traffic vehicle supervision method and system | |
| Bäumler et al. | Report on validation of the stochastic traffic simulation (Part B) | |
| Tian et al. | Experimental design of integrated platform for demonstration of cooperative vehicle infrastructure systems in china | |
| Bai et al. | A simulation-based approach to determine the location of dedicated transit lane | |
| CN117894181B (en) | Global traffic abnormal condition integrated monitoring method and system | |
| Tumminello et al. | A Microsimulation-Based Modelling Approach for Connected and Automated Vehicles on Roundabouts | |
| CN117894174B (en) | Road traffic safety active management and control method, device and system | |
| Niu et al. | A Comprehensive Evaluation Approach for Vehicle-Infrastructure Cooperation System Using AHP and Entropy Method | |
| Upadhyay et al. | Traffic Monitoring System using YOLOv3 Model |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181106 |
|
| RJ01 | Rejection of invention patent application after publication |