CN109886474B - Closed test field planning method for automatic driving vehicle test - Google Patents
Closed test field planning method for automatic driving vehicle test Download PDFInfo
- Publication number
- CN109886474B CN109886474B CN201910069177.XA CN201910069177A CN109886474B CN 109886474 B CN109886474 B CN 109886474B CN 201910069177 A CN201910069177 A CN 201910069177A CN 109886474 B CN109886474 B CN 109886474B
- Authority
- CN
- China
- Prior art keywords
- test
- road
- planning
- automatic driving
- functional block
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention relates to a closed test field planning method for an automatic driving vehicle test, which comprises the steps of automatic driving technology test scene demand collection, functional block division, test scene matching, to-be-planned road element extraction, layered partition planning, comprehensive evaluation and optimization selection and the like. Compared with the prior art, the closed test field planning method for the automatic driving vehicle test, provided by the invention, takes the field boundary of the test field and the automatic driving test scene requirement as input, and can obtain a planning scheme of the closed test field road of the automatic driving vehicle, so that the situation that the planning process is adjusted too dependently on subjective experience is avoided.
Description
Technical Field
The invention relates to the technical field of planning and optimization of test fields of automatic driving vehicles, in particular to a closed test field planning method for automatic driving vehicle testing.
Background
A large amount of testing, evaluating and verifying work is required in the development process of the automatic driving technology, and on one hand, various typical application scenes in real life need to be simulated and reproduced in the process; on the other hand, the test scene is required to be controllable and repeatable, the test safety is required to be high, and the test result can be measured.
The traditional test field which is concentrated on the vehicle dynamic and fatigue durability tests cannot well meet the requirements of the automatic driving tests on environment simulation, the open road tests have a large amount of uncertainty, and only the automatic driving vehicles with fully proven safety and reliability can enter the open road to be tested, so that a special closed test field with special equipment and infrastructure is necessary to be reconstructed for test and verification before the automatic driving vehicles get on the road. However, a closed test field planning method for the automatic driving vehicle test is not found at present.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provide a closed test field planning method for the automatic driving vehicle test, which takes the field boundary of a test field and the requirements of an automatic driving test scene as input and can obtain a planning scheme of a closed test field road of an automatic driving vehicle, thereby avoiding the situation that the planning process excessively depends on subjective experience adjustment.
The purpose of the invention can be realized by the following technical scheme:
step 1: collecting basic data of the test scene requirements of the automatic driving technology from government departments, automatic driving related enterprises and scientific research institutions to obtain a test scene requirement table;
step 2: determining a test field functional block partition set B { B } 1 ，B 2 ，…，B n And a test scenario set S' { S) correspondingly deployed in each functional block 1 ’，S 2 ’，…，S n ’}；
And step 3: for any 1 ≦ i ≦ n, from the test scenario subset S i ' extract the road elements, and quantify the size requirement of the road elements, obtain the functional block subset B i The subset A of road elements to be planned which needs to be included in the system i ', n and i are natural numbers.
And 4, step 4: for any 1-n, i is more than or equal to n, according to the subset A of road elements to be planned i ' determining a subset of functional blocks B i A feasible planning scheme for planning road elements between the inner blocks and the blocks;
and 5: and (4) optimizing an optimal scheme from the feasible planning schemes by utilizing a comprehensive evaluation model.
In step 1, the specific method for obtaining the test scenario requirement table is as follows:
collecting autodrive test scenario demand base data from a plurality of sources, comprising: testing scene requirements of ADAS standard regulations, testing scene requirements of enterprise research and development units, testing scene requirements of scientific research projects, testing scene requirements extracted based on large-scale natural driving acquisition data, testing scene requirements extracted based on Chinese traffic accident database, and collecting and recording a testing scene set as S { S } 1 ，S 2 ，…，S m And m is the number of test scenes.
In step 2, the specific method for determining the test field functional block division and the corresponding test scene set S' is as follows:
step 2.1, determining the planning priority of the functional blocks based on the importance degree and the specificity degree of each functional block;
step 2.2, combining the area and the topographic characteristics of the test field, determining the breadth and the depth of the functional block division in the test field according to the planning priority of the functional blocks, thereby determining the hierarchical division of the functional blocks in the test field and obtaining a functional block division set B { B } of the test field 1 ，B 2 ，…，B n }。
Step 2.3, determining the mapping relation g between the test scene and the functional block according to the element characteristics of the test scene: s → B, i.e. for any 1 ≦ j ≦ m, determine to collect the test scenario subset S j Correspondingly arranged functional block partitioning subset B i (i is more than or equal to 1 and less than or equal to n), and i and j are natural numbers. Dividing the test scenes into different test scene subsets S' { S 1 ’，S 2 ’，…，S n ’}。
In step 3, the specific method for acquiring the road element set to be planned includes:
for any 1 ≦ i ≦ n, from subset S i ' extracting road elements from the test scene, and calculating the initial distance D required by the test by selecting proper test parameters s Acceleration distance l 1 Constant velocity distance l 2 Measuring distance l 3 Braking distance l 4 And a safety distance l 5 And finally calculating the size requirement L of the road elements:
L＝D s +l 1 +l 2 +l 3 +l 4 +l 5 。
will be selected from the subset S i In the extracted road elements, the road elements with the same road characteristics except the length and the size are combined into the same category, and the road element with the maximum size requirement in each category is added into the subset of the road elements to be planned. For any 1 ≤ i ≤ n, the above operations are performed to obtain a road element set to be planned A' { A [ ] 1 ’，A 2 ’，…，A n ’}。
In step 4, the determination function block B i The effective scheme of the inner road element planning comprises the following specific steps:
for any 1-n, i is more than or equal to n, determining a subset A of road elements to be planned i ' all the road elements in the corresponding functional block B i The arrangement of (1). According to the road planning thought of the layering and partitioning, the road planning inside each functional block and among the functional blocks is sequentially carried out by taking the functional blocks as units. A plurality of feasible planning schemes can be obtained by the planning method.
In step 5, the specific method for preferably selecting the optimal solution from the feasible solutions by using the comprehensive evaluation model comprises the following steps:
step 5.1, collecting expert opinions and constructing an evaluation index system;
step 5.2, an index weight determining stage, wherein the weight of each level of index is determined according to the relative importance of the index, and the index weight is expressed by a normalized vector;
and 5.3, in a comprehensive evaluation stage, determining the score of each feasible planning scheme obtained in the step 4 in each index, and determining the comprehensive score of each planning scheme by combining the weight of each index, wherein the planning scheme with the highest comprehensive score is used as the final planning scheme.
In step 5.1, the stages of constructing the evaluation index system are specifically as follows:
and collecting expert opinions, and determining factors influencing the quality of the test field planning scheme from the aspects of engineering construction and practical application so as to determine an evaluation index system.
In step 5.2, the index weight determining stage specifically includes:
the relative importance between every two indexes is determined by means of pairwise comparison judgment, and the judgment is expressed by numerical values by introducing proper scales, so that a judgment matrix is established. And after the consistency of the judgment matrix is checked, solving the characteristic vector of the judgment matrix as the weight coefficient vector of each evaluation index.
In step 5.3, the comprehensive evaluation stage specifically comprises:
firstly, determining an index score according to an index mapping value, wherein the index mapping value has two expression forms: and obtaining a semantic measured value by qualitative evaluation indexes and an accurate measured value by quantitative evaluation indexes. Converting the semantic evaluation value into a score value represented by a numerical value; for the accurate measurement and evaluation value, the optimal measurement and evaluation value of the index is taken as a judgment basis, and the closer the actual measurement and evaluation value of the index is to the optimal measurement and evaluation value, the higher the score value of the index is. And after the score values of all the indexes of the planning scheme are obtained, the comprehensive score value is calculated by combining the index weight, and the scheme with the highest comprehensive score value is selected as the final planning scheme. Methods available at this stage include, but are not limited to, fuzzy comprehensive evaluation method, TOPSIS, gray correlation method, BP neural network method.
Compared with the prior art, the invention has the following advantages:
(1) According to ADAS standard and regulation, enterprise research and development units, scientific research projects, large-scale natural driving collected data and national traffic accident database collection test scene requirements, the closed test field can meet the requirements of development and verification of automatic driving vehicles at the present stage.
(2) The test field is divided into different functional modules, so that the automatic driving vehicle test with different performance levels can be performed in different functional blocks, and the test confidentiality and the test continuity are ensured.
(3) By calculating the initial distance D s Acceleration distance l 1 Constant velocity distance l 2 And a test distance l 3 Braking distance l 4 And a safety distance l 5 The size requirement of the road elements is determined, so that the road length can meet the test requirement, and the test safety is ensured.
(4) And obtaining the optimal scheme in the feasible schemes by utilizing the comprehensive evaluation model, and providing theoretical guidance for selecting the optimal site planning scheme.
Drawings
FIG. 1 is a flow chart of the present invention for road planning for an autonomous driving closed test site;
FIG. 2 is a schematic diagram of a planned land for an automatic driving closed test field in the embodiment of the invention;
FIG. 3 is a partition diagram of the functional blocks of the test field in the embodiment of the present invention;
fig. 4 shows two closed test field planning schemes for the automated driving vehicle test in the embodiment of the present invention, where fig. 4 (a) is a scheme one, and fig. 4 (b) is a scheme two.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, shall fall within the scope of protection of the present invention.
Examples
The invention provides a closed test field planning method for automatic driving vehicle test, taking the planning of an automatic driving closed test field in a certain city as an example, the planning land of the test field is shown in figure 2, and a curve is the boundary of the planning land. The implementation flow chart is shown in fig. 1, and the detailed description is as follows:
step 1: and collecting the basic data of the requirements of the automatic driving test scene from a plurality of sources. The design goal of the test yard is to meet the test requirements of the autopilot technology to develop and validate the autopilot technology. The optimization and design requirements of the test field are based on the test scene requirements, and the test requirement sources include: the collected part of the test scene requirements are shown in table 1, wherein the test scene requirements of ADAS standard regulations, the test scene requirements of enterprise research and development units, the test scene requirements of scientific research projects, the test scene requirements extracted based on natural driving acquisition data and the test scene requirements extracted based on Chinese traffic accident databases are shown in the table. The number of collected test scenarios is 128, and the collection of test scenarios is denoted as S { S } 1 ，S 2 ，…，S 128 }。
TABLE 1 partial test scenario requirements
| Source | Test scenario |
| ADAS Standard and regulations | s 1 Automatic emergency brake test, s 2 Adaptive cruise test, s 3 Lane departure warning test … |
| Enterprise research and development unit | s 11 Road sign warning, s 12 Lane change assist, s 13 Traffic congestion assistance … |
| Scientific research project | s 62 Attenuation of shock wave, s 63 Intelligent Path planning test, s 64 Dangerous vehicle speed reminding … |
| Data collection for natural driving | s 89 Cutting of road vehicle into the front lane, s 90 Cutting out current lane, s from front vehicle 91 In-out ring island … |
| Traffic accident database | s 109 Crossing by a pedestrian in front, s 110 Non-motor vehicle equidirectional running … |
In step 2, the determining the test field functional block partition B and the test scene set S' correspondingly deployed in the functional block includes the following steps:
and 2.1, determining the planning priority of the functional blocks based on the importance degree and the specificity degree of each functional block. The functional block planning priorities determined in this example are as follows, '>' the left functional block planning priority is higher than the right functional block:
urban road, continuous loop, dynamic square, expressway, ADAS test area, country road, cross-country road and mountain road
Step 2.2, combining the area and the topographic characteristics of the test field, determining the breadth and the depth of the functional block division in the test field, thereby determining the hierarchical division of the functional block in the test field, and dividing the test field into n functional blocks B { B } 1 ，B 2 ，…，B n }. In this example, considering that the area of the enclosed test site is small, the test site is divided into four functional blocks, namely, B { B1 continuous loop, B2 highway, B3 urban road, and B4 dynamic square } with the highest planning priority, the highway and the urban road are divided into a plurality of sub-functional blocks, and the functional blocks of the test site are divided as shown in fig. 2.
Step 2.3, determining the mapping relation g between the test scene and the functional block according to the element characteristics of the test scene: s → B, i.e. for any 1 ≦ j ≦ 128, determine to collect the test scenario subset S j Correspondingly arranged functional block partitioning subset B i (i is more than or equal to 1 and less than or equal to 4). Thereby dividing the test scenes into different test scene sets S' { S 1 ’，S 2 ’，S 3 ’，S 4 '}, S' all test scenarios are arranged in the i-th functional block. As follows:
S 1 ' { automatic emergency braking test, adaptive cruise test, lane departure warning test … };
S 2 ' { expressway access and ramp test, emergency lane parking, passing through expressway toll station … };
S 3 ' { automatic auxiliary passage in narrow road, pedestrian crossing ahead, non-motor vehicle syntropy travel, road sign warning … };
S 4 ' { curve speed early warning test, automatic continuous steering test … }.
In step 3, the following steps are included:
step 3.1, extracting road elements and calculating size requirements: for any 1 ≦ i ≦ 4, from subset S i ' extracting road elements from each test scene, and calculating the initial distance D required by the test by selecting proper test parameters s Acceleration distance l 1 Constant velocity distance l 2 Measuring distance l 3 Braking distance l 4 And a safety distance l 5 And finally calculating the size requirement L of the road elements:
L＝D s +l 1 +l 2 +l 3 +l 4 +l 5 。
by subset S i The automatic emergency braking test in' is an example, and the test scenario is that the test vehicle approaches a front stationary vehicle at a speed of 80 km/h. The speed of a test vehicle is required to reach 80km/h before entering a test road section, the test vehicle runs at the constant speed for 2s, and then the test vehicle enters the test road section for testing. TTC =4s of the test vehicle from a stationary vehicle ahead at the start of the test, assuming an acceleration of the vehicle of 0.25g and a braking deceleration of 0.6g during the test. The road elements of the test scene are straight roads, the width is at least a single lane, and the size requirement is calculated as follows:
L＝D s +l 1 +l 2 +l 3 +l 4 +l 5 ＝306m
the road element of the test scene is a straight road with the length of 306m and the width of at least a single lane.
Step 3.2, merging the road elements with the same road characteristics except the length size into the same category from the road elements extracted from the subset Si'; adding the road elements with the maximum size requirement in each category to the subset A of the road elements to be planned i ' of (1). For any 1 ≤ i ≤ 4, the above operations are performed to obtain a road element set to be planned A' { A [ ] 1 ’，A 2 ’，A 3 ’，A 4 ’}，A’All the road elements in (B) need to be arranged in the i-th functional block B i In (1). As follows:
A 1 ' { four-lane straight lane 700m in length, curve 125m in radius, curve 250m in radius, and curve … 500m in radius };
A 2 ' { entrance ramp, exit ramp, four-lane straight run … of length 600m };
A 3 ' { roundabout, crossroad, T-shaped intersection, staggered intersection, 3m long and narrow lane with width of 120m and length of 550m four-lane straight lane … };
A 4 ' { circle square with radius not less than 250m }.
In step 4, the subset B of functional blocks is determined i The feasible scheme of the inner road element planning comprises the following steps: for any 1-n, i is more than or equal to n, determining a subset A of road elements to be planned i ' all road elements in the corresponding functional block subset B i The arrangement of (1). According to the road planning idea of hierarchical partitioning, the road planning inside each functional block and among the functional blocks is performed in sequence by taking the functional blocks as units, as shown in fig. 3.
A first layer of continuous loops according to a subset A of road elements to be planned 1 ' comprises the elements of curves with the radius of 125m, 250m and 500m, four-lane straight roads with the length of 700m and the like, and is arranged on the outermost side;
the second layer of expressway is arranged on the inner side of the continuous loop, is parallel to the longest straight road of the continuous loop, has the length of no less than 600m, plans a transition road among the expressway, the continuous loop and the urban road, and simulates an exit ramp and an entrance ramp of the expressway;
the third layer of urban roads simulates typical urban intersections and urban roads of different grades through the urban road networks which are mutually staggered;
and the dynamic square of the fourth layer is arranged at one end of the expressway, has the radius of 260m, and can be used as an acceleration section before high-speed testing and a deceleration section and safety margin after high-speed testing.
Two possible autopilot test suite planning schemes are obtained in this example, as shown in fig. 4 (a) and 4 (b), respectively.
In step 5, the method for optimizing the optimal solution from the feasible solutions by using the comprehensive evaluation model comprises the following steps:
and 5.1, establishing a test field evaluation index. From the perspective of engineering construction and practical application, a test field evaluation index set is determined to be W { W1 engineering cost, W2 engineering time consumption, W3 land utilization condition, W4 test safety and W5 test efficiency } through an expert survey method.
And 5.2, determining the index weight. The relative importance between every two indexes is determined by experts in a pairwise comparison and judgment mode, and then a judgment matrix M is constructed. Each element M in M cd The relative importance scale represents the relative importance degree of the index c relative to the index d, and the numerical values and corresponding meanings of the scales are shown in table 5.
TABLE 5 analytic hierarchy Process relative importance Scale and implications
Among the several scale values, when the scale values are taken to be 2, 4, 6, 8, 1/2, 1/4, 1/6, 1/8, it means that the importance levels are between the scale levels in Table 5. In this example, the results shown in Table 6 were obtained for five evaluation indexes W1 to W5:
TABLE 6 importance relation 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 the matrix M is judged to be:
solving the eigenvector of the judgment matrix M to obtain the weight vector
Thus, the weights of the evaluation indexes are respectively:
TABLE 7 evaluation index weights
| Evaluation index | W1 | W2 | W3 | W4 | W5 |
| Index weight | 0.041 | 0.087 | 0.2 | 0.2 | 0.471 |
Calculating the maximum characteristic root gamma of the judgment matrix M max And the consistency test is carried out on the =5.1156, so that the consistency of the multi-factor judgment idea logic of an evaluator is ensured, the judgment is coordinated and consistent, and the result of internal contradiction is avoided. The consistency index c.i. is:
as long as it satisfies
The judgment result of the comparison matrix is considered to satisfy the consistency, in this example
And the consistency requirement is met, namely the obtained index weight vector is acceptable.
The method available in the comprehensive evaluation stage of step 5.3 includes, but is not limited to, a fuzzy comprehensive evaluation method, a TOPSIS, a gray correlation method, and a BP neural network method, and the example is explained by applying the fuzzy comprehensive evaluation method. The fuzzy comprehensive evaluation method converts qualitative evaluation into quantitative evaluation according to the membership principle, and has a good practical effect on evaluating the problems of intellectuality, such as fuzziness and difficulty in quantification.
Step 5.3.1, firstly, a comment set C { C1 is good, C2 is good, C3 is general, C4 is poor and C5 is poor }, and step 5.3.2, the planning scheme is issued to ten experts, so that each expert determines the comment of each index, namely the membership (namely frequency distribution) of each index to each comment grade is determined, and the evaluation vector of each evaluation index is obtained. For example, for the "W1 project cost" index, if three experts give a good comment of C1, five experts give a good comment of C2, and the remaining two experts give a general comment of C3, the evaluation vector of the index is (0.3,0.5,0.2,0,0).
Step 5.3.3 performing the above operation on each index to obtain a fuzzy evaluation matrix T, wherein each element T in the matrix T ef Indicating the degree of membership of the e-th index to the f-th comment.
Step 5.3.4 uses the evaluation index weight vector
And carrying out synthetic operation on the fuzzy evaluation matrix T so as to obtain a fuzzy comprehensive evaluation result G.
Step 5.3.5 adds a corresponding score μ = (1.0,0.8,0.6,0.4,0.2) to the comment set, and calculates a comprehensive evaluation score as follows:
Score＝Bμ T
in this example, score =0.8571 is calculated, and similarly, a total evaluation Score of 0.5924 is obtained for solution two, so that solution one is selected as the final solution.
While the invention has been described with reference to specific embodiments, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (4)
1. A closed test field planning method for an automatic driving vehicle test is characterized by comprising the following steps:
s1: collecting basic data of the test scene requirements of the automatic driving technology from government departments, automatic driving related enterprises and scientific research institutions to obtain a test scene requirement table;
s2: determining a test field functional block partition set B { B } 1 ，B 2 ，…，B n And a test scenario set S' { S) correspondingly deployed in each functional block 1 ’，S 2 ’，…，S n ’}；
S3: extracting road elements from any test scene set, quantifying the size requirement of the road elements, and obtaining a road element set A' to be planned, which is required to be contained in a functional block division set B;
s4: determining a feasible scheme for the road element planning in the functional block division set B and among the blocks according to any road element set A' to be planned;
s5: obtaining an optimal scheme in the feasible schemes by utilizing the comprehensive evaluation model;
the step S2 comprises the following sub-steps:
s201: determining the planning priority of each functional block based on different characteristics of each functional block;
s202: according to the planning priority of each functional block, each functional block is divided to obtain a test field functional block division set B { B } 1 ，B 2 ，…，B n }；
S203: determining the mapping relation with the functional blocks according to the element characteristics of the test scene, determining the functional blocks correspondingly arranged in the test scene, and dividing the test scene into different test scene subsets S according to the corresponding functional blocks i ', combined to form a set of test scenarios S' { S 1 ’，S 2 ’，…，S n ’}；
In step S3, the specific method for obtaining the road element set to be planned includes:
for any 1 ≦ i ≦ n, from subset S i ' extracting roads from the test scenarioElement for calculating initial distance required by test by selecting proper test parameters
Acceleration distance
At a uniform speed
Measuring distance
Braking distance
And a safe distance
Finally, calculating the size requirement of the road element
：
Will be selected from the subset S i In the extracted road elements, the road elements with the same road characteristics except the length dimension are merged into the same category, the road element with the maximum dimension requirement in each category is added into the subset of the road elements to be planned, and the operation is carried out on any 1 ≤ i ≤ n to obtain the set of road elements to be planned A' { A ≤ and 1 ’，A 2 ’，…，A n ’}。
2. the method for planning the closed test field facing the automatic driving vehicle test according to claim 1, wherein the basic data of the test scenario requirement in the step S1 comprises: the basic data of the test scene requirements in ADAS standard regulations, the basic data of the test scene requirements put forward by enterprise research and development units, the basic data of the test scene requirements put forward by scientific research projects, the basic data of the test scene requirements extracted based on large-scale natural driving collected data and the basic data of the test scene requirements extracted based on a Chinese traffic accident database.
3. The method for planning the closed test field facing the automatic driving vehicle test according to claim 1, wherein the step S5 comprises the following sub-steps:
s501: constructing an evaluation index system;
s502: determining the weight of each level index according to the characteristic difference among the indexes;
s503: and determining each index score of the feasible schemes in the step S4 and a comprehensive score after the weights are collected, wherein the scheme with the highest comprehensive score is the optimal scheme.
4. The method for planning the closed test field facing the automatic driving vehicle test as claimed in claim 3, wherein the method adopted in the step S503 comprises any one of fuzzy comprehensive evaluation method, TOPSIS method, grey correlation method and BP neural network method.
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 CN109886474A (en) | 2019-06-14 |
| CN109886474B true 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) |
Families Citing this family (7)
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
Citations (3)
| 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 |
| 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 |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9926607B2 (en) * | 2015-03-26 | 2018-03-27 | Women's College Hospital | Breast cancer biomarkers and methods of using same |
-
2019
- 2019-01-24 CN CN201910069177.XA patent/CN109886474B/en active Active
Patent Citations (3)
| 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 |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109886474A (en) | 2019-06-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109886474B (en) | Closed test field planning method for automatic driving vehicle test | |
| CN110298500B (en) | Urban traffic track data set generation method based on taxi data and urban road network | |
| CN107330217B (en) | Mesoscopic oil consumption prediction method based on RBFNN | |
| CN109840660A (en) | A kind of vehicular characteristics data processing method and vehicle risk prediction model training method | |
| CN111275965B (en) | Real-time traffic simulation analysis system and method based on internet big data | |
| CN106056903B (en) | The detection method in the road congestion region based on GPS data | |
| CN111008505A (en) | Urban ramp driving condition construction method and application | |
| CN110836675A (en) | Decision tree-based automatic driving search decision method | |
| CN107180534B (en) | The express highway section average speed estimation method of support vector regression fusion | |
| CN103456163A (en) | City expressway interchange traffic capacity and running status discrimination method and system | |
| CN111710160A (en) | Travel time prediction method based on floating car data | |
| Cunha et al. | Genetic algorithm for the calibration of vehicle performance models of microscopic traffic simulators | |
| Pandey et al. | Assessment of Level of Service on urban roads: a revisit to past studies. | |
| Garnaik et al. | Impact of highway design on traffic safety: how geometric elements affect accident risk | |
| Sekhar et al. | Analysis of travel time reliability of an urban corridor using micro simulation techniques | |
| Kukadapwar et al. | Modeling of traffic congestion on urban road network using fuzzy inference system | |
| CN115206104B (en) | Urban resident traffic trip mode identification method based on mobile phone signaling data | |
| CN110867075A (en) | Method for evaluating influence of road speed meter on reaction behavior of driver under rainy condition | |
| CN106529118A (en) | Two-tuple linguistic AHP based intelligent automobile human-simulated steering control performance evaluation method | |
| Gong et al. | Calibrating microscopic traffic simulation models using speed-flow data. | |
| CN114973668B (en) | Urban road traffic weak link identification method based on topological step number analysis | |
| CN117238131B (en) | Traffic flow characteristic analysis method in Internet of vehicles environment | |
| CN116703039B (en) | Station city fusion data analysis method and device | |
| Bao et al. | Understanding children's cycling route selection through spatial trajectory data mining | |
| Kalinic et al. | Floating car data and fuzzy logic for classifying congestion indexes in the city of Shanghai |
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 |