CN109886474A - A kind of closed test field planing method towards automatic driving vehicle test - Google Patents
A kind of closed test field planing method towards automatic driving vehicle test Download PDFInfo
- Publication number
- CN109886474A CN109886474A CN201910069177.XA CN201910069177A CN109886474A CN 109886474 A CN109886474 A CN 109886474A CN 201910069177 A CN201910069177 A CN 201910069177A CN 109886474 A CN109886474 A CN 109886474A
- Authority
- CN
- China
- Prior art keywords
- test
- mac function
- driving vehicle
- test scene
- automatic driving
- 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.)
- Granted
Links
Landscapes
- Traffic Control Systems (AREA)
Abstract
The present invention relates to it is a kind of towards automatic driving vehicle test closed test field planing method, including collections of automatic Pilot technical testing scene demand, mac function division, test scene matching, road elements recognition to be planned, layering and zoning plan, overall merit select excellent step.Compared with prior art, closed test field planing method provided by the invention towards automatic driving vehicle test, it is input with the place boundary of checkout area, automatic Pilot test scene demand, the programme of autonomous driving vehicle closed test field road can be obtained, to avoid excessively relying on subjective experience adjustment in planning process.
Description
Technical field
The present invention relates to the planning of automatic driving vehicle checkout area and optimisation technique field, more particularly, to one kind towards automatic
Drive the closed test field planing method of vehicle testing.
Background technique
It needs largely to be tested, evaluated and verified work in the development process of automatic Pilot technology, in this process
Middle one side needs to simulate the various typical case scenes in reproduction real-life;On the other hand, it is desirable that test scene is controllable, can
It repeats, Security of test is high and test result can measure.
Tradition is absorbed in power performance and the test site of fatigue durability test cannot meet automatic Pilot test very well
Demand to environmental simulation, and open route test has a large amount of uncertainties, only safety and reliability is sufficiently proved
Autonomous driving vehicle can enter open route be tested, it is therefore necessary to again construction have special installation and basis
Work is verified in the dedicated closed test field of facility, the test on autonomous driving vehicle before road.But at present not yet discovery towards
The closed test field planing method of automatic driving vehicle test.
Summary of the invention
It is an object of the present invention to overcome the above-mentioned drawbacks of the prior art and provide one kind towards automatic Pilot
The closed test field planing method of vehicle testing is input, energy with the place boundary of checkout area, automatic Pilot test scene demand
The programme for enough obtaining autonomous driving vehicle closed test field road, to avoid excessively relying on subjective experience in planning process
Adjustment.
The purpose of the present invention can be achieved through the following technical solutions:
Step 1: collecting automatic driving technology test scene from government department, automatic Pilot relevant enterprise, scientific research institution and need
Master data is sought, test scene demand schedule is obtained;
Step 2: determining that checkout area mac function divides set B { B1, B2..., BnAnd in the corresponding deployment of each mac function
Test scene set S ' { S1', S2' ..., Sn'};
Step 3: for arbitrary 1≤i≤n, from test scene subclass Si' in extract road element, and quantify
The size requirement of road element, obtains mac function subclass BiThe middle road element subclass A to be planned for needing to includei', n and i
It is natural number.
Step 4: for arbitrary 1≤i≤n, according to road element subclass A to be plannedi' determine mac function subclass
BiThe feasible programme of interior and inter-block road element planning;
Step 5: preferably going out optimal case from feasible programme using comprehensive evaluation model.
It is in step 1, described to obtain test scene demand schedule method particularly includes:
Collect the automatic Pilot test scene demand master data in multiple sources, comprising: the checkout area of ADAS Standard andRegulation
The test scene demand of test scene demand, Science Research Project proposition that scape demand, Corporation R & D unit propose is advised based on big
Mould is driven the test scene demand of acquisition data extraction naturally, is needed based on the test scene that Chinese transportation incident database extracts
It asks, collects test scene set and be denoted as S { S1, S2..., Sm, m is test scene number.
In step 2, the determining checkout area mac function divides and corresponds to the specific method of test scene set S '
Are as follows:
Importance degree and particularity degree of the step 2.1 based on each mac function, determine the plan priority of mac function
Grade;
The area and lineament of step 2.2 binding test field determine checkout area according to the plan priority grade of mac function
The range and depth that middle mac function divides, so that it is determined that the distinguishing hierarchy of mac function and obtaining checkout area function in checkout area
Block divides set B { B1, B2..., Bn}。
Step 2.3 determines mapping relations g:S → B of test scene and mac function according to the element characteristic of test scene,
I.e. for arbitrary 1≤j≤m, determines and collect test scene subclass SjThe mac function dividing subset of corresponding arrangement closes Bi(1≤
I≤n), i, j are natural number.Test scene is divided into different test scene subset S ' { S according to corresponding mac function1',
S2' ..., Sn’}。
It is in step 3, described to obtain road elements combination to be planned method particularly includes:
For arbitrary 1≤i≤n, from subset Si' test scene in extract road element, it is suitable by selecting
Test parameter tests required initial distance D to calculates, acceleration distance l1, at the uniform velocity distance l2, measuring distance l3, braking distance l4
With safe distance l5, finally calculate the size requirement L of road element:
L=Ds+l1+l2+l3+l4+l5。
It will be from subset Si' extract road element in, remaining roadway characteristic road element all the same in addition to length dimension
Same category is merged into, the road element that full-size in each classification is required is added to road element subclass to be planned
In.For arbitrary 1≤i≤n, progress aforesaid operations, road elements combination A ' { A to be planned is obtained1', A2' ..., An’}。
In step 4, the determining mac function BiThe effective scheme of interior road element planning method particularly includes:
For arbitrary 1≤i≤n, road element subclass A to be planned is determinedi' in all road elements in corresponding function
It can block BiIn arrangement.Roading thinking according to layering and zoning successively carries out each function as unit of mac function
Roading inside energy block and between mac function.Several feasible programmes can be obtained by above-mentioned planing method.
It is described preferably to go out optimal case from feasible program using comprehensive evaluation model in step 5 method particularly includes:
Step 5.1 collects expert opinion, constructs assessment indicator system;
Step 5.2 index weights determine the stage, the weight of each level index are determined according to the relative importance of index, this refers to
Mark weight is indicated with normalized vector;
The step 5.3 overall merit stage, determine each of obtained in step 4 feasible programme each index
Point, the comprehensive score of each programme is determined in conjunction with each index weights, is made with the highest programme of wherein comprehensive score
For final programme.
In step 5.1, the building assessment indicator system stage specifically:
Expert opinion is collected, determining from engineering construction and practical application angle influences checkout area programme superiority and inferiority
Factor, so that it is determined that assessment indicator system.
In step 5.2, the index weights determine the stage specifically:
The relative importance between every two index is determined by way of multilevel iudge two-by-two, these judgements pass through introducing
Suitable scale is showed with numerical value, and then establishes judgment matrix.After test and judge matrix consistency, judgment matrix is solved
Weight coefficient vector of the feature vector as each evaluation index.
In step 5.3, the overall merit stage specifically:
It is first depending on index assessment value and determines index score value, there are two types of the forms of expression for index assessment value: qualitative evaluation refers to
The accurate determination value that the semantic assessment value and quantitative assessing index that mark obtains obtain.For semantic assessment value, it is translated into number
It is worth the score value indicated;For accurate determination value, using the optimal assessment value of the index as judgment basis, the practical assessment of the index
It is worth closer to optimal assessment value, then the score value of the index is higher.Programme is obtained to combine after the score value of each index
Index weights calculate comprehensive score value, select the highest scheme of comprehensive score value as final programme.The stage is available
Method includes but is not limited to Field Using Fuzzy Comprehensive Assessment, TOPSIS, Gray Correlation, BP neural network method.
Compared with prior art, the invention has the following advantages that
(1) data are acquired by ADAS Standard andRegulation, Corporation R & D unit, Science Research Project, extensive drive naturally
Test scene demand is collected with Chinese transportation incident database, so that closed test field can satisfy automatic driving vehicle at this stage
Exploitation and verifying require.
(2) checkout area is divided into different function module, the automatic of different performance level can be carried out in different function block
Vehicle testing is driven, ensure that test confidentiality and test continuity.
(3) by calculating initial distance Ds, acceleration distance l1, at the uniform velocity distance l2, measuring distance l3, braking distance l4And safety
Distance l5The size requirement for determining road element, so that link length can satisfy test request, and ensure that Security of test.
(4) optimal case in feasible program is obtained using comprehensive evaluation model, mention for optimal site planning Scheme Choice
Theoretical direction is supplied.
Detailed description of the invention
Fig. 1 is the flow chart of automatic Pilot closed test of the present invention field roading;
Fig. 2 is automatic Pilot closed test field planned land use schematic diagram in the embodiment of the present invention;
Fig. 3 is that checkout area mac function divides figure in the embodiment of the present invention;
Fig. 4 is two kinds of closed test field programmes towards automatic driving vehicle test in the embodiment of the present invention,
Middle Fig. 4 (a) is scheme one, and Fig. 4 (b) is scheme two.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiment is a part of the embodiments of the present invention, rather than whole embodiments.Based on this hair
Embodiment in bright, those of ordinary skill in the art's every other reality obtained without making creative work
Example is applied, all should belong to the scope of protection of the invention.
Embodiment
The invention proposes a kind of closed test field planing methods towards automatic driving vehicle test, with the automatic of certain city
For driving the planning of closed test field, checkout area planned land use is as shown in Fig. 2, curve is planned land use boundary.Its implementing procedure
Figure is as shown in Figure 1, detailed description are as follows:
Step 1: collecting the automatic Pilot test scene demand master data in multiple sources.The design object of checkout area is full
The testing requirement of sufficient automatic Pilot technology, automatic Pilot technology is developed and be verified.The optimization and design of checkout area need
Will be using test scene demand as foundation, testing requirement source includes: the test scene demand of ADAS Standard andRegulation, Corporation R & D list
The test scene demand of test scene demand, Science Research Project proposition that position proposes is extracted based on nature driving acquisition data
Test scene demand, based on Chinese transportation incident database extract test scene demand, the partial test scene being collected into
Demand is as shown in table 1.The test scene number being collected into is 128, will collect test scene set and is denoted as S { S1, S2..., S128}。
1 partial test scene demand of table
Source | Test scene |
ADAS Standard andRegulation | s1Automatic emergency brake test, s2Adaptive cruise test, s3Lane departure warning test ... |
Corporation R & D unit | s11Road sign prompting, s12Lane-change auxiliary, s13Traffic congestion auxiliary ... |
Science Research Project | s62Shock wave attenuation, s63Intelligent path planning test, s64Dangerous speed is reminded ... |
Naturally acquisition data are driven | s89Road vehicle incision front lane, s90Front truck cuts out current lane, s91Pass in and out rotary island ... |
Traffic accident database | s109Front pedestrian crosses, s110Non-motor vehicle travels in the same direction ... |
In step 2, the determination checkout area mac function divides B and the test scene in the corresponding deployment of mac function
Set S ' the following steps are included:
Importance degree and particularity degree of the step 2.1 based on each mac function, determine the plan priority of mac function
Grade.Each mac function plan priority grade determined in this example is as follows, and the mac function plan priority grade on ' > ' left side is higher than the right side
The mac function on side:
Urban road > continuous loop > dynamic square > highway > the test section ADAS > backroad > cross-country road > mountain area
Road
The area and lineament of step 2.2 binding test field determine mac function divides in checkout area range and depth
Degree, so that it is determined that in checkout area mac function distinguishing hierarchy, checkout area is divided into n mac function B { B1, B2..., Bn}。
In this example, it is contemplated that closed test field land area is smaller, and checkout area is divided into four big mac functions, respectively plan priority
Highest four mac functions of grade, i.e. B { B1 continuous loop, B2 highway, B3 urban road, B4 dynamic square }, high speed are public
Road and urban road are divided into several subfunction blocks again, and checkout area mac function divides as shown in Figure 2.
Step 2.3 determines mapping relations g:S → B of test scene and mac function according to the element characteristic of test scene,
I.e. for arbitrary 1≤j≤128, determines and collect test scene subclass SjThe mac function dividing subset of corresponding arrangement closes Bi(1
≤i≤4).To which test scene is divided into different test scene set S ' { S according to corresponding mac function1', S2', S3',
S4', all test scenes in S ' are arranged in i-th of mac function.It is as follows:
S1' { automatic emergency brake test, adaptive cruise test, lane departure warning test ... };
S2' { expressway entrance and exit and ring road test, Emergency Vehicle Lane parking pass through freeway toll station ... };
S3' { arrow path is current from dynamic auxiliary, and front pedestrian crosses, and non-motor vehicle travels in the same direction, and road sign is reminded ... };
S4' { bend speed early warning test, automatic continuous slew test ... }.
In step 3, including the following steps:
Step 3.1 extracts road element and calculates size requirement: for arbitrary 1≤i≤4, from subset Si' each test
Road element is extracted in scene, initial distance D needed for test is calculated by selecting suitable test parameters, accelerate away from
From l1, at the uniform velocity distance l2, measuring distance l3, braking distance l4With safe distance l5, finally calculate the size requirement L of road element:
L=Ds+l1+l2+l3+l4+l5。
With subset Si' in automatic emergency brake test for, test scene is that test vehicle is close with 80km/h speed
Front stationary vehicle.Test vehicle needs the speed before entering test segment to reach 80km/h, and drives at a constant speed 2s with the speed,
Enter test segment later to be tested.Start to test TTC=4s of the vehicle away from front stationary vehicle when test, it is assumed that tested
The acceleration of vehicle is 0.25g, braking deceleration 0.6g in journey.The road element of the test scene is straight way, and width is at least
For bicycle road, size requires to calculate as follows:
L=Ds+l1+l2+l3+l4+l5=306m
The road element of the test scene is the straight way of 306m long, and width is at least bicycle road.
Step 3.2 will be from the road element that subset Si ' is extracted, remaining roadway characteristic road all the same in addition to length dimension
Road element merges into same category;The road element that full-size in each classification is required, is added to road element to be planned
Subclass Ai' in.For arbitrary 1≤i≤4, progress aforesaid operations, road elements combination A ' { A to be planned is obtained1', A2',
A3', A4', all road elements in A ' are required to be arranged in i-th of mac function BiIn.It is as follows:
A1' { length 700m Four-Lane Road straight way, the bend of radius 125m, the bend of radius 250m, radius 500m's is curved
Road ... };
A2' { Entrance ramp, exit ramp, the Four-Lane Road straight way ... of length 600m };
A3' { rotary island, cross crossing, T font crossing, staggered cross crossing, long 120m wide 3m arrow path, length 550m tetra-
Lane straight way ... };
A4' { the circle square that radius is not less than 250m }.
In step 4, the determination mac function subclass BiThe feasible program of interior road element planning include: for
Arbitrary 1≤i≤n determines road element subclass A to be plannedi' in all road elements in corresponding function block subclass
BiIn arrangement.Roading thinking according to layering and zoning successively carries out each mac function as unit of mac function
Roading between internal and mac function, it is specific as shown in Figure 3.
First layer continuous loop, according to road element subclass A to be planned1' in including radius 125m, 250m, 500m
The elements such as bend, length 700m Four-Lane Road straight way, and meet and be arranged in outermost;
Second layer highway, highway are arranged on the inside of continuous loop, and parallel with continuous loop longest straight way, long
Degree is not less than 600m, and transition road is planned between highway and continuous loop and urban road, simulates going out, entering for highway
Mouth ring road;
Third layer urban road simulates typical urban intersection by interlaced urban road network, and different
The urban road of grade;
4th layer of dynamic square, dynamic square are arranged in highway one end, and radius 260m both can be used as high speed test
Preceding accelerating sections, and can be used as the braking section after high speed test and safe clearance.
Two kinds of feasible automatic Pilot checkout area programmes are obtained in this example, respectively such as Fig. 4 (a) and Fig. 4 (b) institute
Show.
In steps of 5, the utilization comprehensive evaluation model preferably goes out optimal case, including following step from feasible program
It is rapid:
Step 5.1 establishes checkout area evaluation index.From engineering construction and practical application angle, pass through expert survey
Determine that checkout area evaluation indice is W { W1 project cost, W2 engineering time-consuming, W3 land use situation, W4 Security of test, W5
Testing efficiency }.
Step 5.2 determines index weights.It is determined by way of multilevel iudge two-by-two between every two index by expert
Relative importance, and then Judgement Matricies M.Each of M element mcdFor relative importance scale, it is opposite to represent index c
In the relative importance degree of index d, the numerical value of each scale and corresponding meaning are as shown in table 5.
5 analytic hierarchy process (AHP) relative importance scale of table and meaning
Among these scale numerical value, importance is indicated when scale value is taken as 2,4,6,8,1/2,1/4,1/6,1/8
Scale of the grade in table 5.Result as shown in table 6 is obtained for five evaluation indexes of W1~W5 in this example:
6 different degree relation table of table
W1 | W2 | W3 | W4 | W5 | |
W1 | 1 | 1/3 | 1/5 | 1/5 | 1/8 |
W2 | 3 | 1 | 1/3 | 1/3 | 1/5 |
W3 | 5 | 3 | 1 | 1 | 1/3 |
W4 | 5 | 3 | 1 | 1 | 1/3 |
W5 | 8 | 5 | 3 | 3 | 1 |
Then judgment matrix M are as follows:
The feature vector for solving judgment matrix M obtains weight vectors
This makes it possible to obtain the weights of each evaluation index to be respectively as follows:
7 evaluation criterion weight of table
Evaluation index | W1 | W2 | W3 | W4 | W5 |
Index weights | 0.041 | 0.087 | 0.2 | 0.2 | 0.471 |
Calculate the Maximum characteristic root γ of judgment matrix Mmax=5.1156, consistency check is carried out to it, to guarantee estimator
To the consistency of m ulti-factors judgment thought logic, make it is harmonious between each judge, without the result of internal contradictions.One
Cause property index C.I. are as follows:
As long as meeting
Then think that the judging result of comparator matrix meets consistency, in this exampleMeet coherence request, i.e.,
The index weights vector of acquisition is acceptable.
Step 5.3 overall merit stage available method includes but is not limited to Field Using Fuzzy Comprehensive Assessment, TOPSIS, grey pass
Lian Dufa, BP neural network method, this example application Field Using Fuzzy Comprehensive Assessment are illustrated.Field Using Fuzzy Comprehensive Assessment is according to degree of membership
Qualitative evaluation is converted quantitative assessment by principle, it is this kind of for evaluation intelligence it is fuzzy, be difficult to the problem of quantifying and have preferably
Actual effect.
Step 5.3.1 determines Comment gathers C { C1 is fine, C2 is preferable, C3 is general, C4 is poor, C5 is poor } first, step 5.3.2
Programme is issued to ten experts, each expert is allowed to determine the comment of each index, that is, determines each index to respectively commenting
The degree of membership (i.e. frequency distribution) of language grade, to obtain the evaluation vector of each evaluation index.Such as " W1 engineering is made
Valence " index, sharing the comment that three experts provide is C1 fine, and the comment that five experts provide is C2 preferable, remaining two specially
The comment that family provides is C3 general, then the evaluation vector of the index is (0.3,0.5,0.2,0,0).
Step 5.3.3 carries out aforesaid operations to each index, can obtain a fuzzy evaluating matrix T, in matrix T
Each element tefIndicate e-th of index for the degree of membership of f-th of comment.
Step 5.3.4 evaluation criterion weight vectorSynthesis operation is carried out to fuzzy evaluating matrix T, to be obscured
Comprehensive evaluation result G.
Step 5.3.5 adds corresponding scores μ=(1.0,0.8,0.6,0.4,0.2) to Comment gathers, and synthesis is calculated as follows
Evaluate score:
Score=B μT
Can be calculated Score=0.8571 in this example, the overall merit that scheme two similarly can be obtained is scored at 0.5924, because
This selection scheme one is final scheme.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can readily occur in various equivalent modifications or replace
It changes, these modifications or substitutions should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with right
It is required that protection scope subject to.
Claims (7)
1. a kind of closed test field planing method towards automatic driving vehicle test, which comprises the following steps:
S1: automatic driving technology test scene demand basic number is collected from government department, automatic Pilot relevant enterprise, scientific research institution
According to obtaining test scene demand schedule;
S2: determine that checkout area mac function divides set B { B1, B2..., BnAnd in the corresponding test disposed of each mac function
Scene set S ' { S1', S2' ..., Sn'};
S3: extracting road element from any test scene set and quantifies the requirement of road element size, obtains mac function
It divides in set B and needs the road elements combination A ' to be planned for including;
S4: determine that mac function divides in set B and inter-block road element is advised according to any road elements combination A ' to be planned
The feasible program drawn;
S5: the optimal case in feasible program is obtained using comprehensive evaluation model.
2. a kind of closed test field planing method towards automatic driving vehicle test according to claim 1, feature
It is, the test scene demand master data in the step S1 includes: the test scene demand in ADAS Standard andRegulation is basic
The test scene demand base of test scene demand master data, Science Research Project proposition that data, Corporation R & D unit propose
Notebook data drives the test scene demand master data and be based on Chinese transportation accident that acquisition data are extracted based on extensive naturally
The test scene demand master data that database extracts.
3. a kind of closed test field planing method towards automatic driving vehicle test according to claim 1, feature
Be, the step S2 include it is following step by step:
S201: the different characteristic based on each mac function determines the plan priority grade of each mac function;
S202: according to the plan priority grade of each mac function, each mac function is divided and obtains checkout area mac function
Divide set B { B1, B2..., Bn};
S203: according to the determining mapping relations with mac function of the element characteristic of test scene, the corresponding arrangement of test scene is determined
Mac function, test scene is divided into different test scene subset S according to corresponding mac functioni', combination forms test
Scene set S ' { S1', S2' ..., Sn’}。
4. a kind of closed test field planing method towards automatic driving vehicle test according to claim 1, feature
It is, the road element size in the step S3 is made of six parts, and six part includes: initial distance Ds, accelerate away from
From l1, at the uniform velocity distance l2, measuring distance l3, braking distance l4With safe distance l5。
5. a kind of closed test field planing method towards automatic driving vehicle test according to claim 1, feature
It is, the road element size requires L, describes formula are as follows:
L=Ds+l1+l2+l3+l4+l5。
6. a kind of closed test field planing method towards automatic driving vehicle test according to claim 1, feature
Be, the step S5 include it is following step by step:
S501: building assessment indicator system;
S502: the weight of each level index is determined according to the feature difference between index;
S503: each index score and the comprehensive score after set weight for determining the feasible program in step S4, wherein comprehensive
The scheme for closing highest scoring is optimal case.
7. a kind of closed test field planing method towards automatic driving vehicle test according to claim 6, feature
It is, the adoptable method of step S503 includes Field Using Fuzzy Comprehensive Assessment, TOPSIS method, Gray Correlation and BP nerve
Network method any of them.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910069177.XA CN109886474B (en) | 2019-01-24 | 2019-01-24 | Closed test field planning method for automatic driving vehicle test |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910069177.XA CN109886474B (en) | 2019-01-24 | 2019-01-24 | Closed test field planning method for automatic driving vehicle test |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109886474A true CN109886474A (en) | 2019-06-14 |
CN109886474B CN109886474B (en) | 2023-02-10 |
Family
ID=66926738
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910069177.XA Active CN109886474B (en) | 2019-01-24 | 2019-01-24 | Closed test field planning method for automatic driving vehicle test |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109886474B (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111062567A (en) * | 2019-11-11 | 2020-04-24 | 重庆特斯联智慧科技股份有限公司 | Community service scheduling method and system based on deep learning |
CN111428964A (en) * | 2020-02-25 | 2020-07-17 | 哈尔滨工业大学 | Site planning method for verifying key metering index detection equipment of highway |
CN111735639A (en) * | 2020-05-26 | 2020-10-02 | 清华大学苏州汽车研究院(相城) | Automatic driving scene minimum set generation method for intelligent networked automobile demonstration area |
CN112466123A (en) * | 2021-02-02 | 2021-03-09 | 四川紫荆花开智能网联汽车科技有限公司 | Method for arranging intelligent networking automobile test scene in closed test field |
CN112668077A (en) * | 2020-12-21 | 2021-04-16 | 苏州挚途科技有限公司 | Method and device for determining test site planning data, processor and electronic device |
CN112906209A (en) * | 2021-02-03 | 2021-06-04 | 交通运输部公路科学研究所 | Closed field-oriented train and road cooperative test scene reliability assessment method |
CN117746714A (en) * | 2024-02-20 | 2024-03-22 | 成都运达科技股份有限公司 | Test method and system for simulated driving operation |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107727411A (en) * | 2017-10-30 | 2018-02-23 | 青岛慧拓智能机器有限公司 | A kind of automatic driving vehicle test and appraisal scene generation system and method |
US20180163273A1 (en) * | 2015-03-26 | 2018-06-14 | Women's College Hospital | Breast cancer biomarkers and methods of using same |
CN108332977A (en) * | 2018-01-23 | 2018-07-27 | 常熟昆仑智能科技有限公司 | A kind of classifying and analyzing method joining automotive test scene to intelligent network |
CN108549366A (en) * | 2018-05-04 | 2018-09-18 | 同济大学 | Intelligent automobile road driving mapping experiment method parallel with virtual test |
-
2019
- 2019-01-24 CN CN201910069177.XA patent/CN109886474B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20180163273A1 (en) * | 2015-03-26 | 2018-06-14 | Women's College Hospital | Breast cancer biomarkers and methods of using same |
CN107727411A (en) * | 2017-10-30 | 2018-02-23 | 青岛慧拓智能机器有限公司 | A kind of automatic driving vehicle test and appraisal scene generation system and method |
CN108332977A (en) * | 2018-01-23 | 2018-07-27 | 常熟昆仑智能科技有限公司 | A kind of classifying and analyzing method joining automotive test scene to intelligent network |
CN108549366A (en) * | 2018-05-04 | 2018-09-18 | 同济大学 | Intelligent automobile road driving mapping experiment method parallel with virtual test |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111062567B (en) * | 2019-11-11 | 2021-06-04 | 重庆特斯联智慧科技股份有限公司 | Community service scheduling method and system based on deep learning |
CN111062567A (en) * | 2019-11-11 | 2020-04-24 | 重庆特斯联智慧科技股份有限公司 | Community service scheduling method and system based on deep learning |
CN111428964B (en) * | 2020-02-25 | 2023-06-06 | 哈尔滨工业大学 | Site planning method for calibrating road key metering index detection equipment |
CN111428964A (en) * | 2020-02-25 | 2020-07-17 | 哈尔滨工业大学 | Site planning method for verifying key metering index detection equipment of highway |
CN111735639A (en) * | 2020-05-26 | 2020-10-02 | 清华大学苏州汽车研究院(相城) | Automatic driving scene minimum set generation method for intelligent networked automobile demonstration area |
CN111735639B (en) * | 2020-05-26 | 2022-03-22 | 清华大学苏州汽车研究院(相城) | Automatic driving scene minimum set generation method for intelligent networked automobile demonstration area |
CN112668077A (en) * | 2020-12-21 | 2021-04-16 | 苏州挚途科技有限公司 | Method and device for determining test site planning data, processor and electronic device |
CN112466123A (en) * | 2021-02-02 | 2021-03-09 | 四川紫荆花开智能网联汽车科技有限公司 | Method for arranging intelligent networking automobile test scene in closed test field |
CN112466123B (en) * | 2021-02-02 | 2021-04-23 | 四川紫荆花开智能网联汽车科技有限公司 | Method for arranging intelligent networking automobile test scene in closed test field |
CN112906209A (en) * | 2021-02-03 | 2021-06-04 | 交通运输部公路科学研究所 | Closed field-oriented train and road cooperative test scene reliability assessment method |
CN112906209B (en) * | 2021-02-03 | 2023-07-18 | 交通运输部公路科学研究所 | Closed-field-oriented vehicle-road cooperative test scene credibility assessment method |
CN117746714A (en) * | 2024-02-20 | 2024-03-22 | 成都运达科技股份有限公司 | Test method and system for simulated driving operation |
CN117746714B (en) * | 2024-02-20 | 2024-04-30 | 成都运达科技股份有限公司 | Test method and system for simulated driving operation |
Also Published As
Publication number | Publication date |
---|---|
CN109886474B (en) | 2023-02-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109886474A (en) | A kind of closed test field planing method towards automatic driving vehicle test | |
Calvi et al. | A driving simulator study of driver performance on deceleration lanes | |
CN113065685B (en) | High-precision map traffic rule model based on automatic driving application scene and implementation method thereof | |
CN106530717A (en) | Construction road section risk evaluating method based on cloud model | |
Lai et al. | Optimization of rail transit alignments considering vehicle dynamics | |
Guo et al. | The expressway traffic sign information volume threshold and AGS position based on driving behaviour | |
CN113554877B (en) | Long uphill traffic flow stability improving method based on variable speed limit | |
Wang et al. | Analysis of the driver’s behavior characteristics in low volume freeway interchange | |
Mehrabani et al. | Evaluating the relationship between operating speed and collision frequency of rural multilane highways based on geometric and roadside features | |
CN115375074A (en) | Risk early warning management method for expressway maintenance operation area | |
Zheng | Application of reliability theory to highway geometric design | |
Chu et al. | Application of Pedestrian Microscopic Simulation Technology in Researching the Influenced Realm around Urban Rail Transit Stations | |
CN114973668B (en) | Urban road traffic weak link identification method based on topological step number analysis | |
Wang et al. | Construction Method of AEB Pedestrian Scenario Based on Accident Data | |
DINH et al. | Modeling operating speeds on residential streets with a 30 km/h speed limit: Regression versus neural networks approach | |
CN117238131B (en) | Traffic flow characteristic analysis method in Internet of vehicles environment | |
Chandrasena et al. | A Study of Finding Choice Modle for Class-Wise Railway Passenger Demand for Sri Lanka Railways | |
CN116703039B (en) | Station city fusion data analysis method and device | |
Dastgiri et al. | Development of Analytic Method to Determine Weaving Patterns for Safety Analysis near Freeway Interchanges with Access Management Treatments | |
Gong et al. | Calibrating microscopic traffic simulation models using speed-flow data. | |
Yuan et al. | Research on Warrant of Mid-Block Pedestrian Crosswalk Installation with Synthetic Factors Method | |
Ozkul | Advanced vehicle dynamics modeling approach in traffic microsimulation with emphasis on commercial truck performance and on-board-diagnostics data | |
Ye et al. | Correlation between driver visual characteristics and lane change parameters in urban long-term work zone | |
Alhadidi et al. | The Feasibility and Operational Performance of Implementation Median U-turn Intersections: A CRITIC Method | |
Ekmekçi | An investigation of piecewise Structural Equation Modelling to understand the effect on collisions of shorter visibility designs at urban three arm junctions |
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 |