CN112799964A - Test scene generation method, device, equipment and storage medium - Google Patents
Test scene generation method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN112799964A CN112799964A CN202110284491.7A CN202110284491A CN112799964A CN 112799964 A CN112799964 A CN 112799964A CN 202110284491 A CN202110284491 A CN 202110284491A CN 112799964 A CN112799964 A CN 112799964A
- Authority
- CN
- China
- Prior art keywords
- information
- vehicle
- behavior
- target vehicle
- scene
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/36—Preventing errors by testing or debugging software
- G06F11/3668—Software testing
- G06F11/3672—Test management
- G06F11/3684—Test management for test design, e.g. generating new test cases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/36—Preventing errors by testing or debugging software
- G06F11/3668—Software testing
- G06F11/3672—Test management
- G06F11/3688—Test management for test execution, e.g. scheduling of test suites
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The embodiment of the application discloses a test scene generation method, a test scene generation device, test scene generation equipment and a storage medium, and relates to the field of automatic driving. The method comprises the following steps: reading a road network file, and reading a tested road section according to the tested road section information of the road network file; appointing a participant in a test scene, and loading a model corresponding to the participant; wherein the participants include a host vehicle and a target vehicle; sequentially determining information of each action executed by the vehicle and the target vehicle along with the time migration, wherein the information of each action comprises the action on a tested road section, relative position information between the vehicles, driving lane information, initial/final mark position information and execution means information; and controlling the participants to sequentially execute corresponding behaviors according to the information of each behavior on the tested road section to generate a test scene. The embodiment of the invention ensures that the generation process of the test scene is automatic, convenient to edit and strong in readability.
Description
Technical Field
The embodiment of the application relates to the application software technology of the automatic driving industry, in particular to a test scene generation method, a test scene generation device, test scene generation equipment and a storage medium.
Background
With the development of automated driving, the demand for automated driving tests has increased exponentially, and thus automated driving tests based on analog simulation will replace tens of thousands of actual road tests.
In the process of carrying out the automatic driving simulation test, a test scene is generally required to be manually set up, for example, a test road section, a vehicle and an execution action of the vehicle are manually selected, so that the test efficiency is low, and errors are easy to make.
Disclosure of Invention
The embodiment of the application provides a test scene generation method, a test scene generation device, equipment and a storage medium, so that a test scene is automatically constructed according to information of each behavior executed by time migration, the test scene generation process is automatic, editing is convenient, and readability is high.
In a first aspect, an embodiment of the present application provides a test scenario generation method, including:
reading a road network file, and reading a tested road section according to the tested road section information of the road network file;
appointing a participant in a test scene, and loading a model corresponding to the participant; wherein the participants include a host vehicle and a target vehicle;
sequentially determining information of each action executed by the vehicle and the target vehicle along with the time migration, wherein the information of each action comprises the action on a tested road section, relative position information between the vehicles, driving lane information, initial/final mark position information and execution means information;
and controlling the participants to sequentially execute corresponding behaviors according to the information of each behavior on the tested road section to generate a test scene.
In a second aspect, an embodiment of the present application further provides a test scenario generation apparatus, including:
the reading module is used for reading a road network file and reading a tested road section according to the tested road section information of the road network file;
the system comprises a specifying and loading module, a model obtaining module and a test result obtaining module, wherein the specifying and loading module is used for specifying a participant in a test scene and loading a model corresponding to the participant; wherein the participants include a host vehicle and a target vehicle;
the determining module is used for sequentially determining information of each action executed by the vehicle and the target vehicle along with the time migration, wherein the information of each action comprises the action on a tested road section, relative position information between the vehicles, driving lane information, initial/final mark position information and executing means information;
and the control module is used for controlling the participants to sequentially execute corresponding behaviors according to the information of each behavior on the tested road section and generating a test scene.
In a third aspect, an embodiment of the present application further provides an electronic device, where the electronic device includes:
one or more processors;
a memory for storing one or more programs,
when the one or more programs are executed by the one or more processors, the one or more processors implement the test scenario generation method according to any one of the embodiments.
In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement the test scenario generation method according to any embodiment.
Firstly, reading a road network file, reading a road section to be measured according to the road section information of the road network file, and automatically loading a static scene; on the basis, appointing a participant in the test scene, and loading a corresponding model to realize the loading of the participant; furthermore, the behavior of the participant on the tested road section along with the time migration, the relative position information between vehicles, the driving lane information, the initial/final mark bit information and the execution means information are sequentially determined, so that the behaviors in the test scene are sequentially determined along with the time migration, the participant is controlled to sequentially execute the corresponding behaviors according to the information of the behaviors on the tested road section, the test scene is automatically generated, manual participation is not needed, and the generation efficiency and the accuracy of the test scene are improved. According to the embodiment of the invention, the test scene is described in a more abstract, easier-to-read and easier-to-edit mode by sequentially determining the static scene, the participants and the behaviors which migrate along with time, so that the generation process of the test scene is convenient to edit and has strong readability.
Drawings
Fig. 1 is a flowchart of a test scenario generation method according to an embodiment of the present invention;
FIG. 2 is a flowchart of another test scenario generation method provided in an embodiment of the present invention;
FIG. 3 is a schematic diagram illustrating cutting-out behaviors of two target vehicles in front of a vehicle according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a vehicle with a target cut-in two lanes according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a test scenario generation apparatus according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the application and are not limiting of the application. It should be further noted that, for the convenience of description, only some of the structures related to the present application are shown in the drawings, not all of the structures.
The embodiment of the application provides a test scenario generation method, a flow chart of which is shown in fig. 1, and which is applicable to a situation of building a test scenario in an automatic driving simulation test application scenario. According to the embodiment, the application software in the automatic driving industry is improved, and the building logic of the test scene is optimized by executing a computer program, so that the problems in the prior art are solved.
The method may be performed by a test scenario generation apparatus, which may be constituted by software and/or hardware, and is generally integrated in an electronic device, which is an emulator. With reference to fig. 1, the method provided in this embodiment specifically includes:
s110, reading a road network file, and reading a road section to be measured according to the road section information of the road network file.
The computer program (hereinafter referred to as source code) to be executed in the embodiment of the present invention first describes the road network file and the information of the tested road segments therein, where the information of the tested road segments includes the number, length, and number of lanes of the tested road segments, and thus when the computer program is executed after the source code is compiled, the road network file and the tested road segments therein are read.
The road network file stores a plurality of road segments, and information of one road segment can be designated as information of a tested road segment. The corresponding source code and comments for this step are shown below.
set _ map ("D: \ line4six. xodr")// map setting function expression indicates the storage location of the road network file.
Path _ length (path: p, min _ path _ length: 0meter, max _ path _ length:100meter)// length of the measured link sets a function expression indicating the measured link number p and the length.
The path _ min _ driving _ lanes (p, 2)// number of lanes sets a function expression indicating the number of lanes on the measured road section.
Optionally, in order to distinguish different test scenarios, before the map setting function expression, a scenario expression is further included, as follows:
and the scenario cut _ in// scene expression indicates that the test scene is a cut-in scene.
S120, appointing a participant in a test scene, and loading a model corresponding to the participant; wherein the participants include the host vehicle and the target vehicle. The corresponding source code and comments for this step are shown below.
v1 car// first target vehicle expression
v2 car// second target vehicle expression
The above are all participant (operator) expressions, which represent traffic participants in a test scene, and serve as carriers of dynamic and static behaviors described by the following "action" expression. The type of "actor" may be a vehicle, pedestrian, miscellaneous object, etc. Mathematical models and three-dimensional models that can support "actor" are needed for the simulator. In particular, the participants associate mathematical models and three-dimensional models supported by the simulator.
Optionally, after S120, a default simulator interface path is provided for the road segment under test (the road segment with the number p), so that the road segment with the number p is imported through the simulator interface, which facilitates subsequent determination of the behavior of each participant. An example of source code is as follows:
p:path
and S130, sequentially determining information of each action executed by the vehicle and the target vehicle along with the time transition, wherein the information of each action comprises the action on the tested road section, the relative position information between the vehicles, the driving lane information, the initial/final mark position information and the execution means information.
Optionally, reading each behavior function expression executed by the vehicle and the target vehicle moving along with time, and determining information indicated by each behavior function expression; the behavior function expression comprises a behavior expression, a relative position function expression between vehicles, a driving lane function expression and an execution means function expression;
the behavior expression indicates the tested road section information; the relative position function expression between the vehicles indicates relative position information between the vehicles, and initial/final mark bit information; the driving lane function expression indicates driving lane information and initial/final mark bit information; the execution means function expression indicates execution means information, includes a speed function expression, an acceleration function expression and a lane center offset function expression, and indicates speed information, acceleration information and lane center offset information, respectively. That is, the execution means information includes speed information, acceleration information, and lane center shift amount information.
It should be explained that the initial flag bit information indicates that the participant is in the initial state, and the final flag bit information indicates that the participant is in the final state.
In an application scene, the vehicle, the first target vehicle and the second target vehicle all run on a tested road section at a constant speed. Optionally, the sequentially determining information of each behavior executed by the host vehicle and the target vehicle moving with time includes: determining the behavior, the initial driving lane information and the speed information of the vehicle on the tested road section; determining the behavior and speed information of a first target vehicle on a tested road section, initial relative position information of the first target vehicle and the vehicle and initial driving lane information; and determining the behavior and speed information of the second target vehicle on the measured road section, the initial relative position information of the second target vehicle and the initial driving lane information. The corresponding source code and comments for this step are given below.
(1) Let us drive (path: p)// own vehicle's behavior expression, indicating the driving behavior of the own vehicle on the measured road section p.
Lane (lane:2, at: start)// lane function expression indicates that the host vehicle initially travels on lane 2.
speed (speed: 15.. 18) kph)/speed function expression indicates that the driving speed of the vehicle is any value of 15 kph-18 kph.
(2) v1.drive (path: p) with// the behavior expression of the first target vehicle indicates the driving behavior of the first target vehicle on the measured road section p.
speed (speed: 30.. 50) kph)/speed function expression indicates that the driving speed of the first target vehicle is any value of 30 kph-50 kph.
position (distance: 10..30 meter, while: du.car, at: start)// relative position function expression between vehicles, indicating that the first target vehicle is initially located behind the host vehicle, and the distance from the host vehicle is any value of 10m to 30 m.
And the lane (side _ of: dut. car, side: left, at: start)// driving lane function expression indicates that the lane in which the first target vehicle initially runs is the left lane of the vehicle.
(3) v2.drive (path: p) with// the behavior expression of the second target vehicle indicates the driving behavior of the second target vehicle on the measured road section p.
speed (speed: 70.. 75) kph)/speed function expression indicates that the driving speed of the second target vehicle is any value of 70 kph-75 kph.
position (distance: 10..30 meter, while: du.car, at: start)// relative position function expression between vehicles, indicating that the second target vehicle is initially located behind the host vehicle, and the distance from the host vehicle is any value of 10m to 30 m.
The lane function expression indicates that the lane where the second target vehicle initially travels is the lane on the right side of the vehicle.
Optionally, the execution sequence among the 3 segments of source codes is parallel, and the execution sequence inside each segment of source codes is serial.
In another application scenario, a first target vehicle cuts into the front of the host vehicle. Optionally, the sequentially determining information of each behavior executed by the host vehicle and the target vehicle moving with time includes: determining the behavior of the vehicle on the tested road section; determining the behavior of the target vehicle on the tested road section; determining initial relative driving lane information of the target vehicle and the vehicle and initial relative position information of the target vehicle and the vehicle; determining speed information of the target vehicle; and determining final relative driving lane information of the target vehicle and the vehicle and final relative position information of the target vehicle and the vehicle. The corresponding source code and comments for this step are given below.
(4) Let us drive (path: p)// own vehicle's behavior expression, indicating the driving behavior of the own vehicle on the measured road section p.
(5) v1.drive (path: p) with// the behavior expression of the first target vehicle indicates the driving behavior of the first target vehicle on the measured road section p.
l1 Lane (side of let. car, side: left, at: start)// lane function expression, indicating that the lane in which the first target vehicle initially travels is the left lane of the host vehicle.
p1 (time: 0.5..1] second, ahead _ of: du.car, at: start)// relative position function expression between vehicles, indicating that the first target vehicle initially runs behind the vehicle, and the running time period is any value of 0.5 s-1 s.
speed (speed: 30.. 50) kph)/speed function expression indicates that the driving speed of the first target vehicle is any value of 30 kph-50 kph.
l2 Lane (same _ as: du. car, at: end)// lane function expression indicates that the first target vehicle is eventually traveling in the same lane as the host vehicle.
The expression p2: position (time: [1.5..2] second, ahead _ of dut. car, at: end)// relative position function between vehicles indicates that the first target vehicle is finally located in front of the vehicle to travel, and the travel time period is any value of 1.5-2 s.
Optionally, the execution sequence between the 2 segments of source codes is parallel, and the execution sequence inside each segment of source codes is serial.
In another application scenario, the host vehicle and the target vehicle may continue to travel for a certain distance, and optionally, the information of each action performed by the host vehicle and the target vehicle as they migrate over time is sequentially determined, including: and determining the behavior of the vehicle on the tested road section, and determining the behavior and the speed information of the target vehicle on the tested road section. The corresponding source code and comments in this step are given.
(6) Let us drive (path: p)// own vehicle's behavior expression, indicating the driving behavior of the own vehicle on the measured road section p.
(7) Vehicle 1.drive (path: p) with// the behavior expression of the first target vehicle indicates the traveling behavior of the first target vehicle on the measured road section p.
speed (speed: 40kph)// speed function expression, indicates that the traveling speed of the first target vehicle is 40 kph.
It should be noted that the execution order between the 2 segments of source codes is parallel, and the execution order inside each segment of source codes is serial.
The execution order between the source codes in the above 3 scenarios may be serial. Any one of the 3 application scenarios or the source code in the combined application scenario may be used to generate a test scenario.
Referring to the above description, by sequentially/concurrently executing the function expressions, it is possible to sequentially determine the behavior on the measured road section, the relative position information between the vehicles, the traveling lane information, the initial/final marker bit information, and the execution means information, which are executed as the host vehicle and the target vehicle migrate over time, thereby determining the dynamic scene content that evolves over time.
And S140, controlling the participants to sequentially execute corresponding behaviors according to the information of each behavior on the tested road section, and generating a test scene.
And combining the static scene and the dynamic scene and providing the combined scene to a simulator. And rendering the tested road section and the participants through the simulator, and rendering the test scene frame by frame according to the information of each action executed by the migration along with the time.
Firstly, reading a road network file, reading a road section to be measured according to the road section information of the road network file, and automatically loading a static scene; on the basis, appointing a participant in the test scene, and loading a corresponding model to realize the loading of the participant; furthermore, the behavior of the participant on the tested road section along with the time migration, the relative position information between vehicles, the driving lane information, the initial/final mark bit information and the execution means information are sequentially determined, so that the behaviors in the test scene are sequentially determined along with the time migration, the participant is controlled to sequentially execute the corresponding behaviors according to the information of the behaviors on the tested road section, the test scene is automatically generated, manual participation is not needed, and the generation efficiency and the accuracy of the test scene are improved. According to the embodiment of the invention, the test scene is described in a more abstract, easier-to-read and easier-to-edit mode by sequentially determining the static scene, the participants and the behaviors which migrate along with time, so that the generation process of the test scene is convenient to edit and has strong readability.
It should be emphasized that the implementation of this embodiment relies on the above-described logical architecture of the source code, which has the following advantages: 1) the source code architecture uses a grammar structure of a high-level programming language similar to python, and is very easy to learn and master; 2) the source code architecture has good readability and strong maintainability; 3) the source code architecture is far away from machine language, focuses more on the dynamic elements of the scene and the time sequence itself, and can be easily read and edited even by people without programming experience. Furthermore, on the basis of the innovation of the source code structure, the compiled source code is executed, so that the generation process of the test scene is automatic, convenient to edit and high in readability.
Fig. 2 is a schematic flow chart of another test scenario generation method provided in the embodiment of the present invention, and details a determination process of information of each behavior on the basis of the above embodiments specifically include the following steps:
s210, reading a road network file, and reading a road section to be measured according to the road section information of the road network file.
S220, appointing a participant in a test scene, and loading a model corresponding to the participant; wherein the participants include the host vehicle and the target vehicle.
And S230, determining the execution sequence of the scene-level behaviors and the execution condition of each scene-level behavior.
The scene level behavior comprises at least one of line following, cut-in, cut-out and overtaking; the execution order comprises at least one of a serial execution order, a parallel execution order, and a hybrid execution order; the execution condition includes at least one of an execution duration, an execution trigger condition, and an execution end condition.
The scene-level behaviors are behaviors that override the behaviors of the participants and are comprehensively formed by the behaviors of the vehicle and the target vehicle. A test scenario includes at least one scenario-level behavior, and a scenario-level behavior includes at least one behavior of a participant. Alternatively, the hybrid execution order defines how long before or after one action needs to occur before or after another action occurs. Both the execution trigger condition and the execution end condition may be a time point or a set positional relationship between the vehicles.
Illustratively, the scene-level behavior root expression and the scene-level behavior time sequence expression are read, and the execution sequence of the scene-level behaviors and the execution condition of each scene-level behavior are determined. The corresponding source code and comments for this step are given below.
Do serial ()// scene-row-is the root expression do and serial execution order expression serial, indicating serial execution of its internal scene-level behaviors (start _ after _ dut, change _ lane, go _ on).
The start _ before _ dual: parallel (duration: [1..5] second)// parallel execution order expression parallel indicates that the internal behavior (not shown) is parallel execution and the execution time length is any value of 1 s-5 s.
change _ lane _ parallel (duration: [2..3] second)// parallel execution order expression parallel, indicating that its internal behavior (not shown) is parallel execution and the execution duration is any value from 2s to 3 s.
go _ on: parallel (duration: 5 second)// parallel execution sequential expression parallel, indicating that its internal behavior (not shown) is parallel execution and the execution time is 5 s.
And S240, sequentially determining information of each action executed by the vehicle and the target vehicle along with the time transition in each scene-level action.
The complete source code for generating the test scene is given below, and the execution sequence of the behaviors at each scene level and the execution sequence of the behaviors of the host vehicle and the target vehicle in the behaviors at each scene level are indicated.
1. scenario cut_in:
2. set_map("D:\Line4six.xodr"")
3. path_length(path: p, min_path_length: 0meter, max_path_length:100meter)
4. path_min_driving_lanes(p, 2)
5. v1: car
6. v2: car
7. p: path
8. Do serial ()// scene-row-is the root expression do and serial execution order expression serial, indicating serial execution of its internal scene-level behaviors (start _ after _ dut, change _ lane, go _ on).
9. The parallel execution expression parallel under the scene level behavior start _ while indicates that the internal behaviors (du.car.drive, v1.drive, v 2.drive) are executed in parallel.
10. dut.car.drive(path: p)
11. lane(lane:2, at: start)
12. speed(speed: [15..18]kph)
13. v1.drive(path: p) with:
14. speed(speed: [30..50]kph)
15. position(distance: [10..30]meter, behind: dut.car, at: start)
16. lane(side_of: dut.car, side: left, at: start)
17. v2.drive(path: p) with:
18. speed(speed: [70..75]kph)
19. position(distance: [10..30]meter, behind: dut.car, at: start)
20. lane(side_of: dut.car, side: right, at: start)
21. change _ lane: parallel (duration: [2..3] second)// scene level behavior parallel execution expression parallel under change _ lane, indicating that its internal behaviors (dual.
22. dut.car.drive(path: p)
23. v1.drive(path: p) with:
24. l1: lane(side_of: dut.car, side: left, at: start)
25. p1: position(time: [0.5..1]second, ahead_of: dut.car, at: start)
26. speed(speed: [30..50]kph)
27. l2: lane(same_as: dut.car, at: end)
28. p2: position(time: [1.5..2]second, ahead_of: dut.car, at: end)
29. go _ on: parallel (duration: 5 second)// scene level behavior parallel execution expression under go _ on, indicating that its internal behaviors (duration.
30. dut.car.drive(path: p)
31. v1.drive(path: p) with:
32. speed(speed: 40kph)
The source code further includes: function parameter expressions (including parameter types and non-parameter types, such as speed: [30..50] kph and path: p), function parameter value expressions (such as [1.5..2] second), and variable definition expressions (such as 5-7 pieces of source code).
It is worth noting that the behavior function expression comprises behavior expressions and modifier expressions (such as 23-28 source codes), or only comprises behavior expressions (such as 22 and 30 source codes). Modifier expressions (such as 24-28 source codes) describe relative positions, driving lanes and execution means among vehicles, and comprise relative position function expressions, driving lane function expressions and execution means function expressions among the vehicles. And the modifier expression and the behavior expression are connected by using a with.
And S250, controlling the participants to execute the corresponding scene level behaviors according to the execution sequence and the execution duration of each scene level behavior on the detected road section.
And S260, controlling the participants to sequentially execute corresponding behaviors according to the information of each behavior when executing the corresponding scene-level behaviors, and generating a test scene.
The following describes S250 and S260 in detail with reference to the above 8-32 source codes.
The 3 scene-level behaviors of starting driving (start _ while _ dut), switching in (change _ lane) and continuing driving (go _ on) are executed in series on the road segment to be measured. When the start _ before _ dut is executed, the vehicle runs on the lane 2 of the tested road section p, and the running speed is any value of 15-18 kph; meanwhile, the first target vehicle starts to run from any value of 10-30 meters behind the vehicle on the lane 1 (the left lane of the lane 2) of the detected road section p, and the running speed is any value of 30-50 kph; meanwhile, the second target vehicle starts to run from any value of 10-30 meters behind the vehicle on the lane 3 (the right lane of the lane 2) of the detected road section p, and the running speed is any value of 70-75 kph. The driving time of the vehicle, the first target vehicle and the second target vehicle is the same and is any value of 1 s-5 s.
After the start _ before _ dut is ended, change _ lane is started to be executed, and the host vehicle keeps running on the measured link p. Meanwhile, the first target vehicle starts to be located on the left lane (namely lane 1) of the vehicle, then runs to the front of the vehicle and maintains any value of 0.5 s-1 s, and then runs at any speed value of 30 kph-50 kph, so that the first target vehicle exceeds one end of the vehicle by distance. Then, the first target vehicle runs to the lane of the vehicle (i.e. the lane 2), is positioned in front of the vehicle and maintains any value of 0.5 s-1 s. The execution time of change _ lane is any value from 1s to 5 s.
After the change _ lane execution is finished, go _ on is started, and the vehicle keeps running on the measured road section p. Meanwhile, the first target vehicle travels on the measured road section p at a speed of 40 kph. The running time of the vehicle and the first target vehicle is 5 s.
In the embodiment, the execution sequence of the plurality of scene-level behaviors and the execution conditions of the scene-level behaviors are determined, and in each scene-level behavior, the information of each behavior executed by the vehicle and the target vehicle moving along with the time is sequentially determined, so that the execution sequence and the conditions of each scene-level behavior are flexibly set, the expansion of a test scene is facilitated, and the reading and editing of source codes are facilitated.
In the foregoing embodiment and the following embodiments, before reading the road network file and reading the measured road segment according to the measured road segment information of the road network file, the method further includes: reading a scene number, a scene description and a numerical description; analyzing the scene number to obtain a road type, a tested road section, a vehicle behavior, a target vehicle type, a target vehicle position and a target vehicle behavior; analyzing the scene description to obtain static environment information; selecting fields from a code library according to the road type, the tested road section, the vehicle behavior, the target vehicle type, the target vehicle position, the target vehicle behavior and the static environment information, and combining the fields and the corresponding numerical description to obtain a source code; and compiling the source code and executing the compiled object code. In the process of executing the compiled object code, the test scenario generation method provided in any of the embodiments is implemented, for example, a road network file is read, and a tested road segment is read according to the tested road segment information of the road network file; appointing a participant in a test scene, and loading a model corresponding to the participant; wherein the participants include a host vehicle and a target vehicle; sequentially determining information of each action executed by the vehicle and the target vehicle along with the time migration, wherein the information of each action comprises the action on a tested road section, relative position information between the vehicles, driving lane information, initial/final mark position information and execution means information; and controlling the participants to sequentially execute corresponding behaviors according to the information of each behavior on the tested road section to generate a test scene.
Optionally, the naming number specification of the scene number is X-x.xx-XX-X-xxx.x-XX-00, and the meaning represented by each number is a road type, a detected road section, a vehicle behavior, a target vehicle type, a target vehicle position, a target vehicle behavior and a target vehicle behavior complement in sequence. Illustratively, the naming convention is as follows:
1) road type: h-high speed, K-express, C-urban, P-parking.
2) The section to be tested: m-main road, R-ramp (in r.ir ramp, r.mr enters ramp from main road, r.rm enters main road from ramp), T-tunnel (in t.it tunnel, t.mt enters tunnel from main road, t.tm enters main road from tunnel), S-service area, F-toll station, P-main road straight road, W-main road curve, C-intersection, I-ring intersection, O-overpass, F-overpass, E-parking lot exit, X-parking lot entrance, L-parking lot interior, O-others.
3) The behavior of the vehicle is as follows: LK-round-robin, LC-lane change, SF-crossing straight, TL-crossing left turn, TR-crossing right turn, RV-reverse, TA-turn, pi.f-park (forward), pi.r-park (reverse), po.f-drive (forward), po.r-drive (reverse).
4) The target vehicle type: v-four wheeled vehicles, M-two wheeled vehicles, B-non-motorized bicycles, P-pedestrians, A-animals, T-objects.
5) Target vehicle position: EP-vehicle lane front vehicle, EF-vehicle lane rear vehicle, TD-target lane front vehicle, TG-target lane rear vehicle, LP-left lane front vehicle, RP-right lane front vehicle, LF-left lane rear vehicle, RF-right lane rear vehicle, TDP-front vehicle of target lane front vehicle, EPP-front vehicle of vehicle lane front vehicle, LPP-front vehicle of left lane front vehicle, RPP-front vehicle of right lane front vehicle, TS-target lane side vehicle, TNS-adjacent lane side vehicle of target lane.
(tail in. S co-directional driving,. O reverse directional driving,. H horizontal parking,. V vertical parking)
6) Target vehicle behavior: ST-stationary, LK-circular, LC-lane change, SF-crossing straight, TL-left turn, TR-right turn, CO-crossing, RV-reverse, TA-turn around, AD-reverse, pi.f-park in (forward), pi.r-park in (reverse), po.f-drive out (forward), po.r-drive out (reverse), AM-up drive, MT-move (only applicable to objects), FL-high fall (only applicable to objects).
7) Target vehicle behavior supplement 01-99: is an explanation of the behavior of the supplementary target vehicle, and is an option.
Illustratively, H-M-LK-V-EP.S-LK-01 is analyzed to obtain high speed, main road, circular line, four-wheel motor vehicles, front vehicles of the road, same-direction running, circular line and constant speed.
The scene description explains the information of road type, tested road section, vehicle type, participant type, position, behavior, situation, test function and the like in a text way. According to the description, the scene initial environment setting information, namely static environment information, can be obtained through analysis.
The numerical description defines basic data information of participants and static environment, such as longitudinal initial velocity, transverse initial velocity, acceleration, transverse distance, longitudinal distance, bias rate, action trigger time, action duration, lane width, visibility, temperature and the like.
The numerical description represents the participant behavior-related data in two forms, a scalar numerical value and a numerical range, for example, the host vehicle initial longitudinal speed Ve _ x 0: [50,120] (km/h), headway THW: 5 (s/Veh), etc.
Before selecting the code base field, the code base of the analysis result and the code base field needs to be established in advance, and then the fields corresponding to the road type, the tested road section, the vehicle behavior, the target vehicle type, the target vehicle position, the target vehicle behavior and the static environment information are selected from the code base. The following shows part of the content of the codebase:
TABLE 1 correspondence table of participant types and codebase fields
Type (B) | Code base field |
Four-wheel motor vehicle | car |
Two-wheeled motor vehicle | motor |
Bicycle with a wheel | bike |
Pedestrian | pedestrian |
Animal(s) production | animal |
Object | object |
TABLE 2 correspondence table between target vehicle position and code base field
Type (B) | Code base field |
Front vehicle-same direction of the lane | ahead_of same_as |
Rear vehicle-same direction of the lane | behind same_as |
Front vehicle-same direction of (left) adjacent lane | ahead_of left_of |
Front vehicle-same direction of (right) adjacent lane | ahead_of right_of |
Rear vehicle-same direction of (left) adjacent lane | behind left_of |
Rear vehicle-same direction of (right) adjacent lane | behind right_of |
The code base defines a data structure of basic information and behavior information of the vehicle and the target vehicle, and numerical description is required to be correspondingly combined into corresponding fields of the structure. Illustratively, the fields in the structure that need to incorporate numerical descriptions are as follows:
the vehicle structure includes fields: the vehicle driving system comprises a vehicle initial longitudinal speed Ve _ x0 (km/h), a vehicle transverse speed Ve _ y (m/s), a vehicle longitudinal acceleration Ae _ y (m/s 2), a vehicle lane change duration t(s), a vehicle longitudinal axis and vehicle lane center line offset delta L1 (m), a vehicle longitudinal axis and target lane center line offset delta L2 (m) and the like.
The target vehicle structure body includes fields: initial longitudinal speed Vo1_ x0 (km/h), lateral speed Vo1_ y (m/s), longitudinal acceleration Ao1_ y (m/s 2), initial longitudinal speed Vo2_ x0 (km/h), lateral speed Vo2_ y (km/h), longitudinal acceleration Ao2_ y (m/s 2), initial relative lateral distance Dy0_ o1 (m) from the host vehicle, initial relative longitudinal distance Dx0_ o1 (m) from the host vehicle, lane change duration t 1(s), vehicle offset rate/human (non-motor vehicle) collision point (%), time of collision ttc(s), headway THW (s/Veh).
The static environment information structure includes fields: lane width (m), longitudinal gradient Slope (Slope), number of lanes N (N), driving lane N (nth left), curve radius r (m), illuminance (lux), visibility (m), humidity (% rh), temperature (°), wind power (level), rainfall (mm), and snow accumulation (mm).
After the numerical value description is correspondingly combined into the corresponding fields of the structure body, mapping each field into different code blocks according to functions; and combining the code blocks to obtain the final source code.
Specifically, the first step: and mapping fields and numerical descriptions corresponding to the static environment information to the static scene part of the source code according to the static environment construction standard in the source code, which is referred to the 2-4 source codes.
The second step is that: and mapping fields corresponding to the participants and the tested road sections to a variable definition part of the source code, which is referred to the 5-7 source codes.
The third step: the parallel execution timings of the own-vehicle and target-vehicle behaviors are nested under the serial execution timing, and the parallel execution timings include execution times, see the above-mentioned 8, 9, 21, and 29 pieces of source code.
The fourth step: and mapping the field and the numerical description corresponding to the vehicle part of the source code. Specifically, the initialization state of the host vehicle is set. When the vehicle is not externally connected with an automatic driving algorithm, a constant-speed line patrol operation mode is usually set, which is referred to the 10-12 source codes.
The fifth step: and mapping the corresponding fields and the numerical description of the target vehicle in the initialization state to the target vehicle part of the source code. Specifically, the initialization state of the target vehicle is set, which is referred to in the above 13-20 source codes.
And a sixth step: and mapping the corresponding field and the numerical description after the vehicle/target vehicle is initialized to the vehicle/target vehicle part of the source code. Specifically, fields corresponding to behaviors of the vehicle/target vehicle are obtained, corresponding behavior parameters are combined, and the behavior setting of the vehicle/target vehicle is completed, which is shown in the 22-28 source codes and the 30-32 source codes.
The seventh step: and combining the code blocks to obtain the final source code.
Optionally, the present embodiment further includes an example of reading a picture, as shown in fig. 3 and 4. The picture example can visually display the participant behavior described by the current scene in a visual mode.
According to the method and the device, the source code can be automatically generated according to the information with high readability, such as the scene number, the scene description and the numerical description, programming is not needed, and labor cost and time are saved.
Fig. 5 is a schematic structural diagram of a test scenario generation apparatus provided in an embodiment of the present application, and the embodiment of the present application is suitable for a situation where a test scenario is set up in an automatic driving simulation test application scenario. With reference to fig. 5, the test scenario generation apparatus includes: a read module 410, a specify and load module 420, a determine module 430, and a control module 440.
The reading module 410 is configured to read a road network file, and read a measured road section according to the measured road section information of the road network file;
a specifying and loading module 420, configured to specify a participant in a test scenario and load a model corresponding to the participant; wherein the participants include a host vehicle and a target vehicle;
a determining module 430, configured to sequentially determine information of each behavior executed by the host vehicle and the target vehicle during time transition, where the information of each behavior includes a behavior on a detected road segment, relative position information between vehicles, driving lane information, initial/final mark position information, and execution means information;
and the control module 440 is configured to control the participant to sequentially execute corresponding behaviors according to the information of each behavior on the road segment to be tested, so as to generate a test scene.
Firstly, reading a road network file, reading a road section to be measured according to the road section information of the road network file, and automatically loading a static scene; on the basis, appointing a participant in the test scene, and loading a corresponding model to realize the loading of the participant; furthermore, the behavior of the participant on the tested road section along with the time migration, the relative position information between vehicles, the driving lane information, the initial/final mark bit information and the execution means information are sequentially determined, so that the behaviors in the test scene are sequentially determined along with the time migration, the participant is controlled to sequentially execute the corresponding behaviors according to the information of the behaviors on the tested road section, the test scene is automatically generated, manual participation is not needed, and the generation efficiency and the accuracy of the test scene are improved. According to the embodiment of the invention, the test scene is described in a more abstract, easier-to-read and easier-to-edit mode by sequentially determining the static scene, the participants and the behaviors which migrate along with time, so that the generation process of the test scene is convenient to edit and has strong readability.
Optionally, the determining module 430 is specifically configured to determine an execution order of the multiple scene-level behaviors and an execution condition of each scene-level behavior; and sequentially determining information of each action executed by the host vehicle and the target vehicle along with the time transition in each scene-level action.
Optionally, the scene-level behavior includes at least one of line circulation, cut-in, cut-out, and overtaking; the execution order comprises at least one of a serial execution order, a parallel execution order, and a hybrid execution order; the execution condition includes at least one of an execution duration, an execution trigger condition, and an execution end condition.
Optionally, the control module 440 is specifically configured to: controlling the participants to execute corresponding scene-level behaviors on the tested road section according to the execution sequence and the execution duration of each scene-level behavior; and when the corresponding scene-level behaviors are executed, controlling the participants to sequentially execute the corresponding behaviors according to the information of the behaviors to generate a test scene.
Optionally, the determining module 430 is specifically configured to read each behavior function expression executed by the host vehicle and the target vehicle migrating along with the time, and determine information indicated by each behavior function expression; the behavior function expression comprises a behavior expression, a relative position function expression between vehicles, a driving lane function expression and an execution means function expression; the behavior expression indicates a behavior on the road segment under test; the relative position function expression between the vehicles indicates relative position information between the vehicles, and initial/final mark bit information; the driving lane function expression indicates driving lane information and initial/final mark bit information; the execution means function expression indicates execution means information, includes a speed function expression, an acceleration function expression and a lane center offset function expression, and indicates speed information, acceleration information and lane center offset information, respectively.
Optionally, the determining module 430 is specifically configured to determine a behavior, initial driving lane information, and speed information of the host vehicle on the measured road segment; determining the behavior and speed information of a first target vehicle on a tested road section, initial relative position information of the first target vehicle and the vehicle and initial driving lane information; determining the behavior and speed information of a second target vehicle on a tested road section, initial relative position information of the second target vehicle and the vehicle and initial driving lane information; and/or the presence of a gas in the gas,
the determining module 430 is specifically configured to determine a behavior of the host vehicle on the measured road segment; determining the behavior of the target vehicle on the tested road section; determining initial relative driving lane information of the target vehicle and the vehicle and initial relative position information of the target vehicle and the vehicle; determining speed information of the target vehicle; and determining final relative driving lane information of the target vehicle and the vehicle and final relative position information of the target vehicle and the vehicle.
Optionally, the apparatus further includes a source code generating module, configured to read a scene number, a scene description, and a numerical description before reading the road network file and reading the measured road segment according to the measured road segment information of the road network file; analyzing the scene number to obtain a road type, a tested road section, a vehicle behavior, a target vehicle type, a target vehicle position and a target vehicle behavior; analyzing the scene description to obtain static environment information; selecting fields from a code library according to the road type, the tested road section, the vehicle behavior, the target vehicle type, the target vehicle position, the target vehicle behavior and the static environment information, and combining the fields and the corresponding numerical description to obtain a source code; and compiling the source code and executing the compiled object code.
The test scenario generation device provided by the embodiment of the application can execute the test scenario generation method provided by any embodiment of the application, and has the corresponding functional modules and beneficial effects of the execution method.
Fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, as shown in fig. 6, the electronic device includes a processor 50, a memory 51, an input device 52, and an output device 53; the number of processors 50 in the device may be one or more, and one processor 50 is taken as an example in fig. 6; the processor 50, the memory 51, the input device 52 and the output device 53 in the apparatus may be connected by a bus or other means, as exemplified by the bus connection in fig. 6.
The memory 51, which is a computer-readable storage medium, may be used to store software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the test scenario generation method in the embodiment of the present invention (for example, the reading module 410, the specifying and loading module 420, the determining module 430, and the control module 440 in the test scenario generation apparatus). The processor 50 executes various functional applications of the device and data processing by executing software programs, instructions and modules stored in the memory 51, that is, implements the test scenario generation method described above.
The memory 51 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the memory 51 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, the memory 51 may further include memory located remotely from the processor 50, which may be connected to the device over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 52 is operable to receive input numeric or character information and to generate key signal inputs relating to user settings and function controls of the apparatus. The output device 53 may include a display device such as a display screen.
The embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the test scenario generation method of any embodiment is implemented.
The computer storage media of the embodiments of the present application may take any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, or the like, as well as conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present application and the technical principles employed. It will be understood by those skilled in the art that the present application is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the application. Therefore, although the present application has been described in more detail with reference to the above embodiments, the present application is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present application, and the scope of the present application is determined by the scope of the appended claims.
Claims (10)
1. A test scenario generation method is characterized by comprising the following steps:
reading a road network file, and reading a tested road section according to the tested road section information of the road network file;
appointing a participant in a test scene, and loading a model corresponding to the participant; wherein the participants include a host vehicle and a target vehicle;
sequentially determining information of each action executed by the vehicle and the target vehicle along with the time migration, wherein the information of each action comprises the action on a tested road section, relative position information between the vehicles, driving lane information, initial/final mark position information and execution means information;
and controlling the participants to sequentially execute corresponding behaviors according to the information of each behavior on the tested road section to generate a test scene.
2. The method according to claim 1, wherein said sequentially determining information of each behavior performed by the host vehicle and the target vehicle as they migrate over time comprises:
determining an execution sequence of a plurality of scene-level behaviors and an execution condition of each scene-level behavior;
and sequentially determining information of each action executed by the host vehicle and the target vehicle along with the time transition in each scene-level action.
3. The method of claim 2, wherein the scene level behavior comprises at least one of line following, cut-in, cut-out, and cut-in; the execution order comprises at least one of a serial execution order, a parallel execution order, and a hybrid execution order; the execution condition includes at least one of an execution duration, an execution trigger condition, and an execution end condition.
4. The method according to claim 2, wherein the controlling the participant to execute corresponding behaviors in sequence according to the information of the behaviors on the road segment to be tested to generate a test scenario comprises:
controlling the participants to execute corresponding scene-level behaviors on the tested road section according to the execution sequence and the execution duration of each scene-level behavior;
and when the corresponding scene-level behaviors are executed, controlling the participants to sequentially execute the corresponding behaviors according to the information of the behaviors to generate a test scene.
5. The method according to any one of claims 1-4, wherein said sequentially determining information of each action performed by the host vehicle and the target vehicle as they migrate over time comprises:
reading each behavior function expression executed by the vehicle and the target vehicle along with the time migration, and determining the information indicated by each behavior function expression; the behavior function expression comprises a behavior expression, a relative position function expression between vehicles, a driving lane function expression and an execution means function expression;
the behavior expression indicates a behavior on the road segment under test; the relative position function expression between the vehicles indicates relative position information between the vehicles, and initial/final mark bit information; the driving lane function expression indicates driving lane information and initial/final mark bit information; the execution means function expression indicates execution means information, includes a speed function expression, an acceleration function expression and a lane center offset function expression, and indicates speed information, acceleration information and lane center offset information, respectively.
6. The method according to any one of claims 1-4, wherein said sequentially determining information of each action performed by the host vehicle and the target vehicle as they migrate over time comprises:
determining the behavior, the initial driving lane information and the speed information of the vehicle on the tested road section; determining the behavior and speed information of a first target vehicle on a tested road section, initial relative position information of the first target vehicle and the vehicle and initial driving lane information; determining the behavior and speed information of a second target vehicle on a tested road section, initial relative position information of the second target vehicle and the vehicle and initial driving lane information; and/or the presence of a gas in the gas,
the sequentially determining information of each action executed by the vehicle and the target vehicle along with the time transition comprises the following steps:
determining the behavior of the vehicle on the tested road section; determining the behavior of the target vehicle on the tested road section; determining initial relative driving lane information of the target vehicle and the vehicle and initial relative position information of the target vehicle and the vehicle; determining speed information of the target vehicle; and determining final relative driving lane information of the target vehicle and the vehicle and final relative position information of the target vehicle and the vehicle.
7. The method according to any one of claims 1-4, further comprising, before reading the road network file and reading the road segment under test according to the road segment information of the road network file:
reading a scene number, a scene description and a numerical description;
analyzing the scene number to obtain a road type, a tested road section, a vehicle behavior, a target vehicle type, a target vehicle position and a target vehicle behavior;
analyzing the scene description to obtain static environment information;
selecting fields from a code library according to the road type, the tested road section, the vehicle behavior, the target vehicle type, the target vehicle position, the target vehicle behavior and the static environment information, and combining the fields and the corresponding numerical description to obtain a source code;
and compiling the source code and executing the compiled object code.
8. A test scenario generation apparatus, comprising:
the reading module is used for reading a road network file and reading a tested road section according to the tested road section information of the road network file;
the system comprises a specifying and loading module, a model obtaining module and a test result obtaining module, wherein the specifying and loading module is used for specifying a participant in a test scene and loading a model corresponding to the participant; wherein the participants include a host vehicle and a target vehicle;
the determining module is used for sequentially determining information of each action executed by the vehicle and the target vehicle along with the time migration, wherein the information of each action comprises the action on a tested road section, relative position information between the vehicles, driving lane information, initial/final mark position information and executing means information;
and the control module is used for controlling the participants to sequentially execute corresponding behaviors according to the information of each behavior on the tested road section and generating a test scene.
9. An electronic device, comprising:
one or more processors;
a memory for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the test scenario generation method of any of claims 1-7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out a test scenario generation method according to any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110284491.7A CN112799964B (en) | 2021-03-17 | 2021-03-17 | Test scene generation method, device, equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110284491.7A CN112799964B (en) | 2021-03-17 | 2021-03-17 | Test scene generation method, device, equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112799964A true CN112799964A (en) | 2021-05-14 |
CN112799964B CN112799964B (en) | 2021-08-10 |
Family
ID=75815517
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110284491.7A Active CN112799964B (en) | 2021-03-17 | 2021-03-17 | Test scene generation method, device, equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112799964B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114529651A (en) * | 2022-04-24 | 2022-05-24 | 中国汽车技术研究中心有限公司 | Visual recording equipment for testing actual road of automatic driving automobile |
CN115092177A (en) * | 2022-06-22 | 2022-09-23 | 重庆长安汽车股份有限公司 | ID distribution method and storage medium for target scene of driverless vehicle ramp |
CN117367831A (en) * | 2023-12-06 | 2024-01-09 | 中汽研汽车检验中心(天津)有限公司 | Intelligent driving limit test scene construction method, device and medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111123920A (en) * | 2019-12-10 | 2020-05-08 | 武汉光庭信息技术股份有限公司 | Method and device for generating automatic driving simulation test scene |
CN111579251A (en) * | 2020-04-16 | 2020-08-25 | 国汽(北京)智能网联汽车研究院有限公司 | Method, device and equipment for determining vehicle test scene and storage medium |
CN111797000A (en) * | 2020-05-27 | 2020-10-20 | 中汽数据有限公司 | Scene complexity evaluation method based on gradient lifting decision tree model |
CN111797003A (en) * | 2020-05-27 | 2020-10-20 | 中汽数据有限公司 | Method for building virtual test scene based on VTD software |
CN111967124A (en) * | 2020-06-30 | 2020-11-20 | 中汽数据有限公司 | Generation method for universal amplification of intelligent automobile recombination scene |
US20200406927A1 (en) * | 2019-06-28 | 2020-12-31 | Robert Bosch Gmbh | Method for testing a vehicle system |
-
2021
- 2021-03-17 CN CN202110284491.7A patent/CN112799964B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20200406927A1 (en) * | 2019-06-28 | 2020-12-31 | Robert Bosch Gmbh | Method for testing a vehicle system |
CN111123920A (en) * | 2019-12-10 | 2020-05-08 | 武汉光庭信息技术股份有限公司 | Method and device for generating automatic driving simulation test scene |
CN111579251A (en) * | 2020-04-16 | 2020-08-25 | 国汽(北京)智能网联汽车研究院有限公司 | Method, device and equipment for determining vehicle test scene and storage medium |
CN111797000A (en) * | 2020-05-27 | 2020-10-20 | 中汽数据有限公司 | Scene complexity evaluation method based on gradient lifting decision tree model |
CN111797003A (en) * | 2020-05-27 | 2020-10-20 | 中汽数据有限公司 | Method for building virtual test scene based on VTD software |
CN111967124A (en) * | 2020-06-30 | 2020-11-20 | 中汽数据有限公司 | Generation method for universal amplification of intelligent automobile recombination scene |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114529651A (en) * | 2022-04-24 | 2022-05-24 | 中国汽车技术研究中心有限公司 | Visual recording equipment for testing actual road of automatic driving automobile |
CN114529651B (en) * | 2022-04-24 | 2022-07-22 | 中国汽车技术研究中心有限公司 | Visual recording equipment for testing actual road of automatic driving automobile |
CN115092177A (en) * | 2022-06-22 | 2022-09-23 | 重庆长安汽车股份有限公司 | ID distribution method and storage medium for target scene of driverless vehicle ramp |
CN117367831A (en) * | 2023-12-06 | 2024-01-09 | 中汽研汽车检验中心(天津)有限公司 | Intelligent driving limit test scene construction method, device and medium |
CN117367831B (en) * | 2023-12-06 | 2024-04-09 | 中汽研汽车检验中心(天津)有限公司 | Intelligent driving limit test scene construction method, device and medium |
Also Published As
Publication number | Publication date |
---|---|
CN112799964B (en) | 2021-08-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112799964B (en) | Test scene generation method, device, equipment and storage medium | |
US12024196B2 (en) | Simulation test method for autonomous driving vehicle, computer equipment and medium | |
CN107063711B (en) | Method and apparatus for testing unmanned vehicles | |
CN109557904B (en) | Test method, device, equipment and medium | |
CN107063710B (en) | Method and apparatus for testing unmanned vehicles | |
CN113378413B (en) | Simulation road network platform building system, method, equipment and storage medium based on Vissim | |
CN111797003A (en) | Method for building virtual test scene based on VTD software | |
CN113065257A (en) | Automatic generation method and device of test case, computer equipment and medium | |
CN113272744A (en) | System for monitoring appropriate behavior of autonomous vehicle and method thereof | |
CN113340318A (en) | Vehicle navigation method, device, electronic equipment and storage medium | |
CN115016318A (en) | Fusion method and system of description language of automatic driving simulation test scene | |
CN112799653B (en) | Compiler for generating source code in test scenario and test scenario generation system | |
CN116022130B (en) | Vehicle parking method, device, electronic equipment and computer readable medium | |
WO2022226477A1 (en) | Systems and methods for simulation supported map quality assurance in an autonomous vehicle context | |
CN111368409A (en) | Vehicle flow simulation processing method, device, equipment and storage medium | |
CN110207726B (en) | Navigation broadcasting mode utility evaluation method and system based on driving simulation technology | |
CN110647053A (en) | Automatic driving simulation method and system | |
Zhou et al. | A survey on autonomous driving system simulators | |
CN116952278A (en) | Simulation test method and system for removing perceived map jitter | |
CN113946956A (en) | Passenger-riding parking simulation method and device | |
CN116519316A (en) | Automatic driving test method, device, storage medium and equipment based on behavior tree | |
CN115540880A (en) | Navigation path matching method and device, electronic equipment and storage medium | |
CN115092186A (en) | Vehicle automatic driving method and device, electronic equipment and storage medium | |
CN113788028A (en) | Vehicle control method, device and computer program product | |
CN112684720A (en) | Simulation test method and device |
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 |