CN113742196B - Testing method and device for intelligent driving software of locomotive - Google Patents
Testing method and device for intelligent driving software of locomotive Download PDFInfo
- Publication number
- CN113742196B CN113742196B CN202010461774.XA CN202010461774A CN113742196B CN 113742196 B CN113742196 B CN 113742196B CN 202010461774 A CN202010461774 A CN 202010461774A CN 113742196 B CN113742196 B CN 113742196B
- Authority
- CN
- China
- Prior art keywords
- scene
- sub
- locomotive
- intelligent driving
- data
- 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
- 230000003137 locomotive effect Effects 0.000 title claims abstract description 156
- 238000012360 testing method Methods 0.000 title claims abstract description 79
- 238000000034 method Methods 0.000 claims abstract description 18
- 238000010998 test method Methods 0.000 claims abstract description 11
- 230000006870 function Effects 0.000 claims description 122
- 230000004044 response Effects 0.000 claims description 32
- 230000008859 change Effects 0.000 claims description 22
- 238000004088 simulation Methods 0.000 claims description 18
- 238000012806 monitoring device Methods 0.000 claims 2
- 238000007405 data analysis Methods 0.000 abstract description 8
- 230000000875 corresponding effect Effects 0.000 description 69
- 230000001174 ascending effect Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011022 operating instruction Methods 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000013522 software testing Methods 0.000 description 2
- 238000000638 solvent extraction Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
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
- G06F11/362—Software debugging
-
- 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
- G06F11/362—Software debugging
- G06F11/366—Software debugging using diagnostics
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)
- Electric Propulsion And Braking For Vehicles (AREA)
Abstract
The invention relates to a method and a device for testing intelligent driving software of a locomotive and a computer readable storage medium. The test method comprises the following steps: collecting original sample data of intelligent driving software of a locomotive; performing scene division on the original sample data to obtain a plurality of sub-scene sample data associated with each sub-scene; and testing locomotive intelligent driving software by utilizing each sub-scene sample data. According to the invention, the historical operation data of intelligent driving of the locomotive can be used as an original sample through big data analysis, and all operation scenes are analyzed and refined from the original sample, so that whether the locomotive can normally operate in the operation scenes is tested after the intelligent driving algorithm of the locomotive is updated.
Description
Technical Field
The invention relates to a software testing technology, in particular to a testing method of intelligent driving software of a locomotive and a testing device of the intelligent driving software of the locomotive.
Background
The locomotive is a vehicle for hauling or pushing railway vehicles to run, and does not have a business load function. As intelligent driving applications of locomotives become more and more widespread, the safety requirements and the reliability requirements on intelligent driving software become higher and higher. There is a need in the art for a software testing technique for comprehensively testing intelligent driving software of a locomotive.
However, because of the very many factors that affect intelligent driving of a locomotive, it is difficult for existing test software to analyze and extract each operating scenario of the locomotive, so it is difficult for existing test software to perform comprehensive test evaluation on the intelligent driving software of the locomotive.
In order to overcome the defects in the prior art, the invention provides a testing method of intelligent driving software of a locomotive, a testing device of the intelligent driving software of the locomotive and a computer readable storage medium. By using big data analysis to take historical operation data of intelligent driving of the locomotive as an original sample, the invention can analyze and extract all operation scenes from the historical operation data, so as to test whether the locomotive can normally operate under the operation scenes after the intelligent driving algorithm of the locomotive is updated.
Disclosure of Invention
The following presents a simplified summary of one or more aspects in order to provide a basic understanding of such aspects. This summary is not an extensive overview of all contemplated aspects, and is intended to neither identify key or critical elements of all aspects nor delineate the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form as a prelude to the more detailed description that is presented later.
In order to overcome the defects in the prior art, the invention provides a testing method of intelligent driving software of a locomotive, a testing device of the intelligent driving software of the locomotive and a computer readable storage medium. By using big data analysis to take historical operation data of intelligent driving of the locomotive as an original sample, the invention can analyze and extract all operation scenes from the historical operation data, so as to test whether the locomotive can normally operate under the operation scenes after the intelligent driving algorithm of the locomotive is updated.
The testing method of the intelligent driving software of the locomotive provided by the invention comprises the following steps: collecting original sample data of intelligent driving software of a locomotive; performing scene division on the original sample data to obtain a plurality of sub-scene sample data associated with each sub-scene; and testing the modified locomotive intelligent driving software by utilizing each sub-scene sample data.
Alternatively, in some embodiments of the present invention, the raw sample data may include recorded data of a train operation monitoring apparatus, operator input locomotive operation data, and output data of locomotive intelligent driving software.
Preferably, in some embodiments of the present invention, the step of performing scene division on the raw sample data may include: dividing the scene indicated by the original sample data into a plurality of sub-scenes by using a scene recognition function, and storing each sub-scene sample data in association with a corresponding sub-scene, wherein the output value of the scene recognition function indicates the influence condition of one or more of signal lamp, acting force, speed, line condition and driver operation on the intelligent driving software of the locomotive.
Preferably, in some embodiments of the present invention, the scene recognition function may beWherein said f 1 (Signal) is a signal recognition function, weight value alpha 1 Weights indicating output values of the signal recognition function, the f 2 (f) Weight value alpha as force recognition function 2 A weight indicating an output value of the force recognition function, the f 3 (v) Weight value alpha as a speed recognition function 3 A weight indicating an output value of the speed recognition function, the f 4 (Line) is a Line identification function, weight value α 4 A weight indicating an output value of the line identification function, the f 5 (Op) identifying a function for the driver's operation, the weight value α 5 A weight indicating an output value of the driver operation recognition function.
Preferably, in some embodiments of the present invention, the step of dividing the scene indicated by the original sample data into a plurality of the sub-scenes using a scene recognition function may further include: responsive toAnd dividing the corresponding road section into a sub-scene by being larger than a preset threshold value, wherein the threshold value indicates the standard data quantity of one sub-scene.
Optionally, in some embodiments of the present invention, it may further include: encoding the plurality of sub-scenes with a scene encoding function, the scene encoding function being associated with the sub-scene sample data of a corresponding sub-scene; and responsive to repetition of the encoding of one sub-scene with the encoding of any preceding sub-scene, removing the repeated sub-scene to reduce the scene data.
Preferably, in some embodiments of the present invention, the scene coding function may be F (Code) =c (signal) +c (F) +c (v) +c (Line) +c (Op). The C (signal) may output a corresponding code according to a change condition of the signal lamp, and output the corresponding code again in response to a change of the signal lamp. The C (f) may output a corresponding code according to the applied force and output a corresponding code again in response to the applied force being changed. The C (v) may output a corresponding code according to the speed and output the corresponding code again in response to the speed being changed. The C (Line) may output a corresponding code according to the Line condition and output the corresponding code again in response to the Line condition being changed. The C (Op) may output a corresponding code according to the driver's operation and output a corresponding code again in response to the driver's operation being changed.
Preferably, in some embodiments of the present invention, the line condition may include a ramp condition, a curve condition, and a tunnel condition. The C (Line) may output a corresponding code in response to any one of the ramp condition, the curve condition, and the tunnel condition being changed.
Optionally, in some embodiments of the present invention, the step of removing the repeated sub-scene may include the steps of: and deleting the repeated codes of the sub-scenes and the corresponding sub-scene sample data. The step of testing the modified intelligent driving software of the locomotive comprises the following steps: and testing the modified intelligent driving software of the locomotive by using the simplified scene data.
Alternatively, in some embodiments of the present invention, the step of testing the modified locomotive intelligent driving software may comprise: reading each sub-scene to load corresponding sub-scene sample data; inputting the corresponding sub-scene sample data into the modified intelligent driving software of the locomotive to obtain intelligent driving simulation data of the modified intelligent driving software of the locomotive; and comparing the intelligent driving simulation data with driving sample data of the original intelligent driving software to judge whether the modified intelligent driving software of the locomotive can enable the locomotive to normally operate.
According to another aspect of the present invention, there is provided a testing device for intelligent driving software of a locomotive, configured to execute the testing method provided in any one of the foregoing embodiments. By using the big data analysis to take the historical operation data of the intelligent driving of the locomotive as an original sample, the testing device of the intelligent driving software of the locomotive can analyze and extract all operation scenes from the historical operation data, so that whether the locomotive can normally operate in the operation scenes can be tested after the intelligent driving algorithm of the locomotive is updated.
The testing device of the intelligent driving software of the locomotive provided by the invention comprises a memory and a processor. The processor is coupled to the memory and configured to: collecting original sample data of intelligent driving software of a locomotive; performing scene division on the original sample data to obtain a plurality of sub-scene sample data associated with each sub-scene; and testing the modified locomotive intelligent driving software by each sub-scene sample data.
Alternatively, in some embodiments of the present invention, the raw sample data may include recorded data of a train operation monitoring apparatus, operator input locomotive operation data, and output data of locomotive intelligent driving software.
Preferably, in some embodiments of the present invention, the processor may be further configured to: dividing the scene indicated by the original sample data into a plurality of sub-scenes by using a scene recognition function, and storing each sub-scene sample data in association with a corresponding sub-scene, wherein the output value of the scene recognition function indicates the influence condition of one or more of signal lamp, acting force, speed, line condition and driver operation on the intelligent driving software of the locomotive.
Preferably, in some embodiments of the present invention, the scene recognition function may beWherein said f 1 (Signal) is a signal recognition function, weight value alpha 1 Weights indicating output values of the signal recognition function, the f 2 (f) Weight value alpha as force recognition function 2 A weight indicating an output value of the force recognition function, the f 3 (v) Weight value alpha as a speed recognition function 3 A weight indicating an output value of the speed recognition function, the f 4 (Line) is a Line identification function, weight value α 4 A weight indicating an output value of the line identification function, the f 5 (Op) identifying a function for the driver's operation, the weight value α 5 A weight indicating an output value of the driver operation recognition function.
Preferably, in some embodiments of the present invention, the processor may be further configured to: responsive toAnd dividing the corresponding road section into a sub-scene by being larger than a preset threshold value, wherein the threshold value indicates the standard data quantity of one sub-scene.
Optionally, in some embodiments of the invention, the processor may be further configured to: encoding the plurality of sub-scenes with a scene encoding function, the scene encoding function being associated with the sub-scene sample data of a corresponding sub-scene; and responsive to repetition of the encoding of one sub-scene with the encoding of any preceding sub-scene, removing the repeated sub-scene to reduce the scene data.
Preferably, in some embodiments of the present invention, the scene coding function may be F (Code) =c (signal) +c (F) +c (v) +c (Line) +c (Op). The C (signal) may output a corresponding code according to a change condition of the signal lamp, and output the corresponding code again in response to a change of the signal lamp. The C (f) may output a corresponding code according to the applied force and output a corresponding code again in response to the applied force being changed. The C (v) may output a corresponding code according to the speed and output the corresponding code again in response to the speed being changed. The C (Line) may output a corresponding code according to the Line condition and output the corresponding code again in response to the Line condition being changed. The C (Op) may output a corresponding code according to the driver's operation and output a corresponding code again in response to the driver's operation being changed.
Preferably, in some embodiments of the present invention, the line condition may include a ramp condition, a curve condition, and a tunnel condition. The C (Line) may output a corresponding code in response to any one of the ramp condition, the curve condition, and the tunnel condition being changed.
Optionally, in some embodiments of the invention, the processor may be further configured to: deleting the repeated codes of the sub-scenes and the sub-scene sample data corresponding to the codes; and testing the modified intelligent driving software of the locomotive by using the simplified scene data.
Preferably, in some embodiments of the present invention, the processor may be further configured to: reading each sub-scene to load corresponding sub-scene sample data; inputting the corresponding sub-scene sample data into the modified intelligent driving software of the locomotive to obtain intelligent driving simulation data of the modified intelligent driving software of the locomotive; and comparing the intelligent driving simulation data with driving sample data of the original intelligent driving software to judge whether the modified intelligent driving software of the locomotive can enable the locomotive to normally operate.
According to another aspect of the present invention, there is also provided herein a computer-readable storage medium.
The present invention provides the above computer readable storage medium having computer instructions stored thereon. The computer instructions, when executed by a processor, may implement the test method provided by any of the embodiments described above. By using big data analysis to take historical operation data of intelligent driving of the locomotive as an original sample, the computer readable storage medium provided by the invention can analyze and extract all operation scenes, so that whether the locomotive can normally operate under the operation scenes can be tested after the intelligent driving algorithm of the locomotive is updated.
Drawings
The above features and advantages of the present invention will be better understood after reading the detailed description of embodiments of the present disclosure in conjunction with the following drawings. In the drawings, the components are not necessarily to scale and components having similar related features or characteristics may have the same or similar reference numerals.
FIG. 1 illustrates a flow chart of a method for testing intelligent driving software of a locomotive, according to some embodiments of the present invention.
Fig. 2 illustrates a schematic diagram of a partitioning scenario provided in accordance with some embodiments of the present invention.
Fig. 3 is a schematic structural diagram of a testing device for intelligent driving software of a locomotive according to another aspect of the present invention.
Detailed Description
Further advantages and effects of the present invention will become apparent to those skilled in the art from the disclosure of the present specification, by describing the embodiments of the present invention with specific examples. While the description of the invention will be presented in connection with a preferred embodiment, it is not intended to limit the inventive features to that embodiment. Rather, the purpose of the invention described in connection with the embodiments is to cover other alternatives or modifications, which may be extended by the claims based on the invention. The following description contains many specific details for the purpose of providing a thorough understanding of the present invention. The invention may be practiced without these specific details. Furthermore, some specific details are omitted from the description in order to avoid obscuring the invention.
As described above, because the factors affecting the intelligent driving of the locomotive are very many, it is difficult for the existing test software to analyze and propose each operating scenario of the locomotive, so it is difficult for the existing test software to perform comprehensive test evaluation on the intelligent driving software of the locomotive.
In order to overcome the defects in the prior art, the invention provides a testing method of intelligent driving software of a locomotive, a testing device of the intelligent driving software of the locomotive and a computer readable storage medium. By using big data analysis to take historical operation data of intelligent driving of the locomotive as an original sample, the invention can analyze and extract all operation scenes from the historical operation data, so as to test whether the locomotive can normally operate under the operation scenes after the intelligent driving algorithm of the locomotive is updated.
Referring to fig. 1, fig. 1 is a flow chart illustrating a testing method of intelligent driving software of a locomotive according to some embodiments of the present invention.
As shown in fig. 1, in the method for testing intelligent driving software of a locomotive provided in this embodiment, the method may include the steps of:
101: and collecting original sample data of intelligent driving software of the locomotive.
The raw sample data includes, but is not limited to, recorded data of a train operation monitoring recording device (LKJ), operation data of a locomotive input by a driver, control instruction data and simulation data output by intelligent driving software of the locomotive.
In some embodiments of the present invention, the processor of the testing device of the intelligent driving software of the locomotive may collect the simulation data output by the processor by loading the original intelligent driving software as the original sample data of the intelligent driving software of the locomotive. The original intelligent driving software is locomotive intelligent driving software subjected to safety certification and reliability certification. The simulation data can comprise raw sample data of a large number of different scenes in the simulation road section, and can provide data comparison for locomotive intelligent driving software modified by subsequent testing.
Alternatively, in other embodiments, the processor of the testing device of the intelligent driving software of the locomotive may also obtain the recorded driving data from the train operation monitoring and recording device (LKJ) of a train, and obtain the operation data of the locomotive input by the driver and the control instruction data output by the intelligent driving software of the locomotive from the central control system of the train, so as to be the original sample data of the intelligent driving software of the locomotive. The driver operation refers to an operation instruction manually input by the driver according to a target condition before the intelligent driving is started. The intelligent driving algorithm software can conduct intelligent driving under specified working conditions according to the operation of a driver. Likewise, the data obtained from the train may also contain raw sample data for a number of different scenarios in the simulated road segment, thereby providing data collation for the locomotive intelligent driving software modified for subsequent testing.
As shown in fig. 1, in the method for testing intelligent driving software of a locomotive provided in this embodiment, the method may further include the steps of:
102: and performing scene division on the original sample data.
As described above, the original sample data obtained by the testing device of the intelligent driving software of the locomotive contains data of a large number of different scenes in the simulation road section, and it is difficult to specifically characterize the actual situation of each operation scene.
In some embodiments of the present invention, the processor of the test device for locomotive intelligent driving software may utilize a scene recognition functionThe acquired original sample data is divided into a plurality of sub-scenes to specifically characterize the actual condition of each running scene. In particular, the processor may utilize a scene recognition functionTo divide the scene indicated by the original sample data into a plurality of sub-scenes.
Wherein: f (f) 1 (Signal) is a signal recognition function, weight value alpha 1 Indicating the weight of the output value of the signal recognition function. f (f) 2 (f) Weight value alpha as force recognition function 2 Indicating the weight of the output value of the force recognition function. f (f) 3 (v) Weight value alpha as a speed recognition function 3 Weights indicating the output values of the speed recognition function. f (f) 4 (Line) is a Line identification function, weight value α 4 Indicating the weight of the output value of the line identification function. f (f) 5 (Op) identifying a function for the driver's operation, the weight value α 5 Indicating the weight of the output value of the driver operation recognition function.
In some embodiments, the signalIdentification functionWherein element s 1 ～s n And respectively indicating the influence conditions of different signal lamp changes on intelligent driving algorithm software. Signal recognition function f 1 The output value of (signal) indicates the influence of signal lamp changes on the intelligent driving algorithm software. For example: the green light has the weakest influence on the intelligent driving algorithm software, and the corresponding score is the lowest. If green light is always present in one sub-scene, f 1 (signal) =0.1. If in one sub-scenario the train encounters 1 green light and 1 yellow light, f 1 (signal) =0.1+0.2=0.3, has a stronger influence on intelligent driving algorithm software.
In some embodiments, the force recognition function α 2 f 2 (f)＝f(F max ，F t ，F tc ) Wherein F is max Indicating maximum available force of locomotive, F t Indicating the actual effort of the locomotive, F tc Indicating the rate of change of the actual force per unit time. Force recognition function f 2 (f) The output value of (2) indicates the influence condition of locomotive acting force on intelligent driving algorithm software.
In some embodiments, the speed recognition function Wherein v indicates the current actual speed of the train, a indicates the acceleration of the train, +.>Indicating the rate of change of acceleration. Speed recognition function f 3 (v) The output value of (2) indicates the influence of the train speed on the intelligent driving algorithm software.
In some embodiments, the line identification function α 4 f 4 (Line) =f (Grade, radius, tunnel), wherein Grade indicates a ramp, radius indicates a curve, tunnel indicates a Tunnel. Line identification function f 4 Output value of (Line) indicates Line conditions such as ramp, curve and tunnel to intelligent driving algorithm softwareIs a matter of course.
In some embodiments, the driver operates the recognition function α 5 f 5 (Op) =f (d, l, o), where d indicates the driving direction indicated by the driver operation, 1 indicates the operation level, and o indicates the ATO operation instruction. Driver operation recognition function f 5 The output value of (Op) indicates the impact of the driver operation on the intelligent driving algorithm software.
The above-mentioned driver operation is an operation instruction input by the locomotive driver before entering intelligent driving, for example: specifying a forward direction, specifying an intelligent driving mode, etc. The intelligent driving mode includes, but is not limited to, a regular mode and a spot driving mode. The intelligent driving software of the locomotive can formulate a corresponding control strategy according to the intelligent driving mode so as to control the train to run stably or arrive at a destination at a designated time. In some embodiments, the locomotive driver may input operating instructions during intelligent driving to modify the intelligent driving mode (e.g., change from a regular mode to a spot mode), but not to change the heading of the train.
To sum up, the scene recognition functionThe output value of (2) can indicate the signal lamp, acting force, speed, line condition and influence condition of driver operation on intelligent driving software of locomotive. In some embodiments, sample data for each sub-scene may be stored in association with the corresponding sub-scene.
In some embodiments of the invention, the sum of the weight values may be 1, i.e., α 1 +α 2 +α 3 +α 4 +α 5 =1. At this point, the processor may respond toIs greater than a predetermined threshold (e.g.: for>) And the corresponding road segments are divided into one sub-scene.
Referring to fig. 2, fig. 2 illustrates a schematic diagram of a partitioning scenario provided in accordance with some embodiments of the present invention.
As shown in fig. 2, in using the scene recognition functionThe sub-scenes divided may include sample data indicating various conditions such as signal lights, applied forces, speeds, line conditions, and driver operations. In some embodiments, the processor may calculate the scene recognition function +/every 1s interval as the locomotive is traveling forward>F if the signal lamp is always green 1 (signal) is always equal to 0.1. When a condition that a signal lamp is changed from a green lamp to a green-yellow lamp is met, f 1 The (signal) is increased by 0.2 to 0.3. Similarly, several other scene recognition functions may increment as the scene changes. When- >And the processor can judge that the data generated by the path travelled by the locomotive is enough to test and use intelligent driving software, so that the corresponding path is divided into a sub-scene. That is, the threshold value for dividing the scene may indicate a standard data amount of one sub-scene, that is, a data amount required for performing the test of the intelligent driving software.
As shown in fig. 1, in the method for testing intelligent driving software of a locomotive provided by the invention, the method further includes the steps of:
103: the repeated scenes are removed to reduce the scene data.
In some embodiments of the present invention, the processor of the test device of the locomotive intelligent driving software may utilize a scene encoding function F (Code) versus scene recognition functionThe divided sub-scenes are encoded. Responsive to repetition of encoding of one sub-scene with encoding of any preceding sub-scene, the processorThe repeated sub-scenes can be removed to reduce scene data, so that the data processing load of the processor is reduced to improve the test efficiency.
Specifically, the scene coding function may be F (Code) =c (signal) +c (F) +c (v) +c (Line) +c (Op).
Wherein: c (signal) is a signal coding function, and is suitable for outputting corresponding codes according to the change condition of the signal lamp; c (f) is a force coding function, and is suitable for outputting corresponding codes according to acting force of the locomotive; c (v) is a speed coding function, and is suitable for outputting corresponding codes according to the speed of the train; c (Line) is a Line coding function, and is suitable for outputting corresponding codes according to the Line condition of the train; c (Op) is a driver operation code function, and is suitable for outputting corresponding codes according to the operation instructions input by the driver. That is, the scene coding function F (Code) is associated with the original sample data of the corresponding sub-scene.
Referring to table 1, table 1 illustrates coding rules for signal coding functions provided according to some embodiments of the present invention.
TABLE 1
| Initial signal lamp color | Post-change signal lamp color | Encoding |
| Green light | Green light | S0001 |
| Green light | Green yellow lamp | S0002 |
| Yellow light | Red, yellow, etc | S0003 |
| Yellow 2 lamp | Double yellow lamp | S0004 |
| Double yellow lamp | White lamp | S0005 |
| White lamp | Red and yellow lamp | S0006 |
| White lamp | Green light | S0007 |
| … | … | … |
As shown in table 1, in some embodiments, the signal encoding function C (signal) is adapted to output a corresponding encoding S0001 when it is detected that the signal is continuously holding green. Meanwhile, the scene coding function F (Code) is adapted to add a Code S0001 for the corresponding scene. In some embodiments, the signal encoding function C (signal) is adapted to output the corresponding encoding S0002 again in response to further detection in the same sub-scene that the signal changes from a green light to a green-yellow light, i.e. that the signal changes. Meanwhile, the scene coding function F (Code) is adapted to add the Code S0002 again for the corresponding scene.
It will be appreciated that in other embodiments, those skilled in the art may adjust the codes corresponding to the signal lamp changes according to the actual application requirements to achieve the same effect.
Referring to table 2, table 2 illustrates encoding rules for force encoding functions provided in accordance with some embodiments of the present invention.
TABLE 2
| Actual given moment (negative number represents braking force) | Encoding |
| 0 to-10% | F0001 |
| -10% to-20% | F0002 |
| -20% to-30% | F0003 |
| -30% to-40% | F0004 |
| -40% to-50% | F0005 |
| -50% to-60% | F0006 |
| -60% to-70% | F0007 |
| -70% to-80% | F0008 |
| -80% to-90% | F0009 |
| -90% to-100% | F0010 |
| 0 | F0011 |
| 0 to 10% | F0012 |
| 10 to 20 percent | F0013 |
| 20% to 30% | F0014 |
| 30 to 40% | F0015 |
| 40% to 50% | F0016 |
| 50 to 60 percent | F0017 |
| 60 to 70 percent | F0018 |
| 70 to 80 percent | F0019 |
| 80 to 90 percent | F0020 |
| 90 to 100% | F0021 |
As shown in Table 2, in some embodiments, the force encoding function C (f) may output a corresponding code based on the actual given moment provided by the locomotive, and each force encoding interval may indicate a moment interval of 10% of the maximum available moment. In some embodiments, in response to further detecting a change in the actual given moment of the locomotive in the same sub-scene, the force encoding function C (F) is adapted to output a corresponding Code again to add the corresponding Code to the scene encoding function F (Code).
It can be appreciated that, in other embodiments, those skilled in the art may adjust the moment interval indicated by each coding interval according to the actual application requirement to achieve the corresponding effect.
Referring to table 3, table 3 illustrates encoding rules for a velocity encoding function provided in accordance with some embodiments of the present invention.
TABLE 3 Table 3
| Speed interval | Encoding |
| 0 to 10KM/h | V0001 |
| 10KM/h to 20KM/h | V0002 |
| 20KM/h to 30KM/h | V0003 |
| 30KM/h to 40KM/h | V0004 |
| 40KM/h to 50KM/h | V0005 |
| 50KM/h to 60KM/h | V0006 |
| 60KM/h to 70KM/h | V0007 |
| 70KM/h to 80KM/h | V0008 |
| 80KM/h to 90KM/h | V0009 |
| 90KM/h to 100KM/h | V0010 |
| 100KM/h to 110KM/h | V0011 |
| 110KM/h to 120KM/h | V0012 |
As shown in table 3, in some embodiments, the speed encoding function C (v) may output a corresponding code according to the actual speed of the train, and each speed encoding section may indicate a speed section of 10 KM/h. In some embodiments, in response to further detecting a change in the speed of the train to another coding interval in the same sub-scene, the speed coding function C (v) is adapted to output a corresponding Code again to add the corresponding Code to the scene coding function F (Code).
It is understood that, in other embodiments, a person skilled in the art may optionally adjust the speed interval (e.g. 0.5 KM/h) indicated by each coding interval according to practical application requirements to achieve a corresponding effect.
In some embodiments, the line conditions in which the train is located may include a ramp condition, a curve condition, and a tunnel condition. In response to a change in any one of a ramp condition, a curve condition, and a tunnel condition, the Line coding function C (Line) is adapted to output a corresponding code according to the Line condition in which the train is located.
Referring to tables 4A-4C in combination, table 4A illustrates the encoding rules for a ramp encoding function provided in accordance with some embodiments of the present invention. Table 4B illustrates the encoding rules of the curve encoding function provided in accordance with some embodiments of the present invention. Table 4C illustrates encoding rules for tunnel encoding functions provided in accordance with some embodiments of the present invention.
TABLE 4A
| Ramp | Ramp coding |
| Ascending a slope: gradient of slope<2‰ | G0001 |
| Ascending a slope: gradient of slope<4‰ | G0002 |
| Ascending a slope: gradient of slope<6‰ | G0003 |
| Ascending a slope: gradient of slope<8‰ | G0004 |
| Ascending a slope: gradient of slope<10‰ | G0005 |
| Downhill: gradient of slope<2‰ | G0006 |
| Downhill: gradient of slope<4‰ | G0007 |
| Downhill: gradient of slope<6‰ | G0008 |
| Downhill: gradient of slope<8‰ | G0009 |
| Downhill: gradient of slope<10‰ | G0010 |
| … | … |
TABLE 4B
| Bend encoding parameter 1 | Curve encoding parameter 2 | Bend encoding parameter 3 | Bend encoding |
| Left bend | Radius of curve<500m | Length of curve<500m | R0001 |
| Left bend | Radius of curve<1000m | Length of curve<1000m | R0002 |
| Left bend | Radius of curve<2000m | Length of curve<2000m | R0003 |
| Left bend | Radius of curve<3000m | Length of curve<3000m | R0004 |
| Right elbow | Radius of curve<500m | Length of curve<500m | R0005 |
| Right elbow | Radius of curve<1000m | Length of curve<1000m | R0006 |
| Right elbow | Radius of curve<2000m | Length of curve<2000m | R0007 |
| Right elbow | Radius of curve<3000m | Length of curve<3000m | R0008 |
| … | … | … | … |
TABLE 4C
| Tunnel coding parameters | Tunnel coding |
| Tunnel length < 100m | T0001 |
| Tunnel length < 500m | T0002 |
| Tunnel length < 1000m | T0003 |
| … | … |
As shown in tables 4A-4C, in some embodiments, the Line coding function C (Line) may output a corresponding code based on the Line condition in which the train is located. Each ramp coding interval may indicate a ramp interval of 2%. Each curve encoding interval may indicate a curve radius interval of 500-1000m and a curve length interval. Each tunnel coding interval may indicate a tunnel length interval of 100-500 m. In some embodiments, in response to further detecting in the same sub-scene that the Line condition in which the train is located has changed, the Line coding function C (Line) is adapted to output the corresponding Code again to add the corresponding Code to the scene coding function F (Code).
It can be appreciated that, in other embodiments, a person skilled in the art may adjust the parameter interval indicated by each coding interval according to the actual application requirement to achieve the corresponding effect.
Referring to Table 5, table 5 illustrates coding rules for a driver operation coding function provided in accordance with some embodiments of the present invention.
TABLE 5
As shown in table 5, in some embodiments, the driver operation code function C (Op) may output corresponding codes according to the driver-entered operation instructions, each speed code indicating a specific driver operation instruction. In some embodiments, in response to further detecting that the driver again enters a driver operation instruction in the same sub-scene, the driver operation encoding function C (Op) is adapted to again output a corresponding encoding to increment the scene encoding function F (Code) by the corresponding encoding.
It will be appreciated that in other embodiments, the driver operating instructions for each coded instruction may be adjusted by one skilled in the art to achieve the same effect, depending on the actual application requirements.
By utilizing an artificial intelligence algorithm, the method can automatically identify the operation scene of the locomotive, classify all the sub-scenes according to the original sample data related to each sub-scene, and record the data characteristics of all the scenes so as to ensure that any scene of the locomotive operation cannot be missed, thereby being used for the test software to comprehensively test and evaluate the intelligent driving software of the locomotive. Because artificial intelligence is adopted to classify and count the operation scene, the invention can greatly reduce the manual operation time, thereby improving the test efficiency. In addition, the intelligent driving algorithm test system has an open acquisition interface for original sample data, and can be suitable for any intelligent driving algorithm of the locomotive, so that the test coverage rate of the intelligent driving algorithm of the locomotive is greatly improved.
In some embodiments, through the above-mentioned encoding process of the scene encoding function F (Code) on all the sub-scenes, each sub-scene can obtain an encoding associated with the original sample data therein. The processor of the testing device of the locomotive intelligent driving software can store the sub-scene sample data related to each sub-scene in association with the corresponding scene code so as to provide data comparison for the locomotive intelligent driving software modified by subsequent testing.
Referring to table 6, table 6 shows the encoding of all scenes provided according to some embodiments of the present invention.
TABLE 6
As shown in table 6, the scene code of the scene CJ01 is S0001S 0002F 0001F 0005V 0001G 0001R 0001T 0001O 0004, indicating that the traffic light is continuously green, the traffic light is changed from green to yellow, the applied force is 0 to-10%, the applied force is-40% to-50%, the speed is 0 to 10KM/h, the road condition is an upward slope of < 2%o, the left curve radius is <500m, the curve length is <500m, the tunnel length is <100m, and the driver inputs the operation command for forward driving and the brake operation command.
Scene CJ02 and scene CJ03 have different scene encodings than scene CJ01, indicating that they relate to different conditions than scene CJ 01. Conversely, scene CJ04 has the same scene code as scene CJ01, indicating that it relates to the same operating conditions as scene CJ 01. That is, for the testing device of the intelligent driving software of the locomotive, the scene CJ04 and the scene CJ01 belong to the same scene, and have the same sub-scene sample Data, i.e., cj_data01 and cjdata04 are the same.
In some embodiments, in response to the repetition of the scene encoding of the scene CJ04 and the scene encoding of the scene CJ01, the processor may delete the Data set cj_data04 in the scene CJ04 and the corresponding scene thereof to reduce the scene Data involved in the software test, thereby reducing the Data processing load of the processor to improve the test efficiency.
As shown in fig. 1, in the method for testing intelligent driving software of a locomotive provided by the invention, the method further includes the steps of:
104: and testing the modified intelligent driving software of the locomotive by using the simplified scene data.
After removing the repeated scenes and obtaining the reduced scene Data, the processor of the test device of the locomotive intelligent driving software may first read the sub-scene CJ01 to load the corresponding sub-scene sample Data cj_data01. Then, the processor can dynamically input the sub-scene sample Data CJ_Data01 into the intelligent driving software of the locomotive to be tested so as to obtain intelligent driving simulation Data of the intelligent driving software of the locomotive to be tested. The intelligent driving software of the locomotive to be tested can be modified based on the original intelligent driving software of the locomotive.
And then, the processor of the testing device can compare the intelligent driving simulation data output by the intelligent driving software of the locomotive to be tested with the driving sample data of the original intelligent driving software so as to judge whether the intelligent driving software of the locomotive to be tested can enable the locomotive to normally operate. The driving sample data of the original intelligent driving software can be actual driving data of a train, and also can be simulation data output by the original intelligent driving software.
In some embodiments, if the intelligent driving simulation data output by the intelligent driving software of the locomotive to be tested is consistent with the driving sample data of the original intelligent driving software, or the difference is smaller than a preset safety threshold, the processor may determine that the intelligent driving software of the locomotive to be tested can enable the locomotive to run normally. Otherwise, if the intelligent driving simulation data output by the intelligent driving software of the locomotive to be tested is inconsistent with the driving sample data of the original intelligent driving software and the difference is larger than a preset safety threshold, the processor can judge that the intelligent driving software of the locomotive to be tested cannot normally operate the locomotive and prompt a tester to modify the intelligent driving software of the locomotive to be tested again.
While, for purposes of simplicity of explanation, the methodologies are shown and described as a series of acts, it is to be understood and appreciated that the methodologies are not limited by the order of acts, as some acts may, in accordance with one or more embodiments, occur in different orders and/or concurrently with other acts from that shown and described herein or not shown and described herein, as would be understood and appreciated by those skilled in the art.
According to another aspect of the present invention, there is provided a testing device for intelligent driving software of a locomotive, configured to execute the testing method provided in any one of the foregoing embodiments.
Referring to fig. 3, fig. 3 is a schematic structural diagram of a testing device for intelligent driving software of a locomotive according to another aspect of the present invention.
As shown in fig. 3, the testing device 30 for intelligent driving software of a locomotive provided by the invention comprises a memory 31 and a processor 32. The memory 31 is a computer-readable storage medium on which computer instructions may be stored. The processor 32 is coupled to the memory 31 and configured to execute the computer instructions stored in the memory 31 to implement the testing method according to any one of the embodiments. By using the big data analysis to take the historical operation data of the intelligent driving of the locomotive as an original sample, the testing device 30 of the intelligent driving software of the locomotive provided by the invention can analyze and extract all operation scenes from the historical operation data, so that whether the locomotive can normally operate under the operation scenes can be tested after the intelligent driving algorithm of the locomotive is updated.
According to another aspect of the present invention, there is also provided herein a computer-readable storage medium.
The above-mentioned computer readable storage medium provided by the present invention may be the memory 31 of the test device 30, on which computer instructions are stored. The computer instructions, when executed by the processor 32, may implement the test methods provided in any of the embodiments described above. By using big data analysis to take historical operation data of intelligent driving of the locomotive as an original sample, the computer readable storage medium provided by the invention can analyze and extract all operation scenes, so that whether the locomotive can normally operate under the operation scenes can be tested after the intelligent driving algorithm of the locomotive is updated.
Those of skill in the art would understand that information, signals, and data may be represented using any of a variety of different technologies and techniques. For example, data, instructions, commands, information, signals, bits, symbols, and chips that may be referenced throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields or particles, or any combination thereof.
Those of skill would further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The various illustrative logical modules, and circuits described in connection with the embodiments disclosed herein may be implemented or performed with a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, e.g., a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium may be integral to the processor. The processor and the storage medium may reside in an ASIC. The ASIC may reside in a user terminal. In the alternative, the processor and the storage medium may reside as discrete components in a user terminal.
In one or more exemplary embodiments, the functions described may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software as a computer program product, the functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage media may be any available media that can be accessed by a computer. By way of example, and not limitation, such computer-readable media can comprise RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. Any connection is properly termed a computer-readable medium. For example, if the software is transmitted from a web site, server, or other remote source using a coaxial cable, fiber optic cable, twisted pair, digital Subscriber Line (DSL), or wireless technologies such as infrared, radio, and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of medium. Disk (disk) and disc (disk) as used herein include Compact Disc (CD), laser disc, optical disc, digital Versatile Disc (DVD), floppy disk and blu-ray disc where disks (disk) usually reproduce data magnetically, while discs (disk) reproduce data optically with lasers. Combinations of the above should also be included within the scope of computer-readable media.
The previous description of the disclosure is provided to enable any person skilled in the art to make or use the disclosure. Various modifications to the disclosure will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other variations without departing from the spirit or scope of the disclosure. Thus, the disclosure is not intended to be limited to the examples and designs described herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (17)
1. The method for testing the intelligent driving software of the locomotive is characterized by comprising the following steps of:
collecting original sample data of intelligent driving software of a locomotive;
dividing the scene indicated by the original sample data into a plurality of sub-scenes by using a scene recognition function, wherein the scene recognition function is that Wherein said f 1 (Signal) is a signal recognition function, weight value alpha 1 Weights indicating output values of the signal recognition function, the f 2 (f) Weight value alpha as force recognition function 2 A weight indicating an output value of the force recognition function, the f 3 (v) Weight value alpha as a speed recognition function 3 Indicating the saidWeighting the output value of the speed recognition function, said f 4 (Line) is a Line identification function, weight value α 4 A weight indicating an output value of the line identification function, the f 5 (Op) identifying a function for the driver's operation, the weight value α 5 A weight indicating an output value of the driver operation recognition function;
storing each sub-scene sample data in association with a corresponding sub-scene; and
and testing the modified intelligent driving software of the locomotive by utilizing each sub-scene sample data.
2. The test method of claim 1, wherein the raw sample data includes recorded data of a train operation monitoring device, operation data of a driver input locomotive, and output data of intelligent driving software of the locomotive.
3. The test method of claim 1, wherein the step of dividing the scene indicated by the raw sample data into a plurality of the sub-scenes using a scene recognition function further comprises:
responsive toAnd dividing the corresponding road section into a sub-scene by being larger than a preset threshold value, wherein the threshold value indicates the standard data quantity of one sub-scene.
4. The test method of claim 1, further comprising:
encoding the plurality of sub-scenes with a scene encoding function, the scene encoding function being associated with the sub-scene sample data of a corresponding sub-scene; and
In response to repetition of the encoding of one sub-scene with the encoding of any preceding sub-scene, the repeated sub-scene is removed to reduce scene data.
5. The test method of claim 4, wherein the scene coding function is F (Code) =C (signal) +C (F) +C (v) +C (Line) +C (Op), wherein,
the C (signal) outputs a corresponding code according to the change condition of the signal lamp, and outputs the corresponding code again in response to the change condition of the signal lamp,
the C (f) outputs a corresponding code according to the applied force, and outputs the corresponding code again in response to the applied force being changed,
the C (v) outputs a corresponding code according to the speed, and outputs the corresponding code again in response to the speed being changed,
the C (Line) outputs a corresponding code according to a Line condition, and outputs the corresponding code again in response to a change in the Line condition,
the C (Op) outputs a corresponding code according to a driver's operation, and outputs a corresponding code again in response to a change in the driver's operation.
6. The test method of claim 5, wherein the line conditions include a ramp condition, a curve condition, and a tunnel condition,
The C (Line) outputs a corresponding code in response to a change in any one of the ramp condition, the curve condition, and the tunnel condition.
7. The method of testing of claim 4, wherein the step of removing the repeated sub-scenario comprises: deleting the repeated codes of the sub-scenes and the corresponding sub-scene sample data thereof,
the step of testing the modified intelligent driving software of the locomotive comprises the following steps: and testing the modified intelligent driving software of the locomotive by using the simplified scene data.
8. The method of testing of claim 1, wherein the step of testing the modified locomotive intelligent driving software comprises:
reading each sub-scene to load corresponding sub-scene sample data;
inputting the corresponding sub-scene sample data into the modified intelligent driving software of the locomotive to obtain intelligent driving simulation data of the modified intelligent driving software of the locomotive; and comparing the intelligent driving simulation data with driving sample data of the original intelligent driving software to judge whether the modified intelligent driving software of the locomotive can enable the locomotive to normally operate.
9. The utility model provides a testing arrangement of locomotive intelligent driving software which characterized in that includes:
A memory; and a processor coupled to the memory and configured to:
collecting original sample data of intelligent driving software of a locomotive;
dividing the scene indicated by the original sample data into a plurality of sub-scenes by using a scene recognition function, wherein the scene recognition function is that Wherein said f 1 (Signal) is a signal recognition function, weight value alpha 1 Weights indicating output values of the signal recognition function, the f 2 (f) Weight value alpha as force recognition function 2 A weight indicating an output value of the force recognition function, the f 3 (v) Weight value alpha as a speed recognition function 3 A weight indicating an output value of the speed recognition function, the f 4 (Line) is a Line identification function, weight value α 4 A weight indicating an output value of the line identification function, the f 5 (Op) identifying a function for the driver's operation, the weight value α 5 A weight indicating an output value of the driver operation recognition function;
storing each sub-scene sample data in association with a corresponding sub-scene; and
and testing the modified intelligent driving software of the locomotive by utilizing each sub-scene sample data.
10. The test device of claim 9, wherein the raw sample data includes recorded data of a train operation monitoring device, operator input locomotive operation data, and output data of locomotive intelligent driving software.
11. The test apparatus of claim 9, wherein the processor is further configured to:
responsive toAnd dividing the corresponding road section into a sub-scene by being larger than a preset threshold value, wherein the threshold value indicates the standard data quantity of one sub-scene.
12. The test apparatus of claim 9, wherein the processor is further configured to:
encoding the plurality of sub-scenes with a scene encoding function, the scene encoding function being associated with the sub-scene sample data of a corresponding sub-scene; and responsive to repetition of the encoding of one sub-scene with the encoding of any preceding sub-scene, removing the repeated sub-scene to reduce the scene data.
13. The test apparatus of claim 12, wherein the scene coding function is F (Code) =c (signal) +c (F) +c (v) +c (Line) +c (Op), wherein,
the C (signal) outputs a corresponding code according to the change condition of the signal lamp, and outputs the corresponding code again in response to the change condition of the signal lamp,
the C (f) outputs a corresponding code according to the applied force, and outputs the corresponding code again in response to the applied force being changed,
The C (v) outputs a corresponding code according to the speed, and outputs the corresponding code again in response to the speed being changed,
the C (Line) outputs a corresponding code according to a Line condition, and outputs the corresponding code again in response to a change in the Line condition,
the C (Op) outputs a corresponding code according to a driver's operation, and outputs a corresponding code again in response to a change in the driver's operation.
14. The test device of claim 13, wherein the line conditions include a ramp condition, a curve condition, and a tunnel condition,
the C (Line) outputs a corresponding code in response to a change in any one of the ramp condition, the curve condition, and the tunnel condition.
15. The test apparatus of claim 12, wherein the processor is further configured to:
deleting the repeated codes of the sub-scenes and the sub-scene sample data corresponding to the codes; and testing the modified intelligent driving software of the locomotive by using the simplified scene data.
16. The test apparatus of claim 9, wherein the processor is further configured to:
reading each sub-scene to load corresponding sub-scene sample data;
Inputting the corresponding sub-scene sample data into the modified intelligent driving software of the locomotive to obtain intelligent driving simulation data of the modified intelligent driving software of the locomotive; and comparing the intelligent driving simulation data with driving sample data of the original intelligent driving software to judge whether the modified intelligent driving software of the locomotive can enable the locomotive to normally operate.
17. A computer readable storage medium having stored thereon computer instructions which, when executed by a processor, implement the test method of any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010461774.XA CN113742196B (en) | 2020-05-27 | 2020-05-27 | Testing method and device for intelligent driving software of locomotive |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010461774.XA CN113742196B (en) | 2020-05-27 | 2020-05-27 | Testing method and device for intelligent driving software of locomotive |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113742196A CN113742196A (en) | 2021-12-03 |
| CN113742196B true CN113742196B (en) | 2024-04-12 |
Family
ID=78723766
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010461774.XA Active CN113742196B (en) | 2020-05-27 | 2020-05-27 | Testing method and device for intelligent driving software of locomotive |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113742196B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116909260B (en) * | 2023-09-12 | 2023-12-01 | 常州星宇车灯股份有限公司 | Intelligent driving domain controller test verification method for simulating HIL (high-performance liquid chromatography) rack |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109032103A (en) * | 2017-06-09 | 2018-12-18 | 百度在线网络技术（北京）有限公司 | Test method, device, equipment and the storage medium of automatic driving vehicle |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10118628B2 (en) * | 2017-02-21 | 2018-11-06 | Allstate Insurance Company | Data processing system for guidance, control, and testing autonomous vehicle features and driver response |
| US20200097004A1 (en) * | 2018-09-25 | 2020-03-26 | Cyngn, Inc. | Evolutionary algorithmic state machine for autonomous vehicle planning |
-
2020
- 2020-05-27 CN CN202010461774.XA patent/CN113742196B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109032103A (en) * | 2017-06-09 | 2018-12-18 | 百度在线网络技术（北京）有限公司 | Test method, device, equipment and the storage medium of automatic driving vehicle |
Non-Patent Citations (1)
| Title |
|---|
| 基于交通事故的自动驾驶虚拟测试方法研究;张珊;王蕾;郭魁元;张嘉芮;刘少华;;中国汽车(第05期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113742196A (en) | 2021-12-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103562978B (en) | Vehicle data analysis method and vehicle data analysis system | |
| CN112069888B (en) | Vehicle checking method and system, road side equipment, vehicle-mounted equipment and handheld terminal | |
| CN110188797B (en) | Intelligent automobile rapid test method based on Bayesian optimization | |
| CN111046049B (en) | Truck GPS track data compression method | |
| CN111351499B (en) | Path identification method and device, computer equipment and computer readable storage medium | |
| CN105741553A (en) | Method for identifying parking road segment in vehicle track based on dynamic threshold | |
| CN107590999B (en) | Traffic state discrimination method based on checkpoint data | |
| CN111242015A (en) | Method for predicting driving danger scene based on motion contour semantic graph | |
| CN112461299B (en) | Turnout section track feature identification method and device | |
| CN111144485B (en) | Vehicle accident judging method and system based on xgboost classification algorithm | |
| CN110749455A (en) | Unmanned vehicle converging traffic flow passing capacity testing system and testing method | |
| CN113742196B (en) | Testing method and device for intelligent driving software of locomotive | |
| CN114881076B (en) | Rail corrugation identification method, device, equipment and medium based on support vector machine | |
| CN113127466B (en) | Vehicle track data preprocessing method and computer storage medium | |
| CN115279643A (en) | On-board active learning method and apparatus for training a perception network of an autonomous vehicle | |
| CN110264725B (en) | Method and device for determining road section flow | |
| CN114973681B (en) | In-transit vehicle sensing method and device | |
| CN113299060B (en) | Vehicle information coefficient acquisition system based on measured data | |
| CN116092033A (en) | Vehicle track data driven vehicle lane change starting and ending point identification method | |
| CN115527076B (en) | Construction method and system of abnormal driving behavior recognition model of commercial vehicle | |
| CN112346969B (en) | AEB development verification system and method based on data acquisition platform | |
| CN113935189A (en) | Train braking capacity prediction method, electronic equipment and computer storage medium | |
| CN116997890A (en) | Generating an unknown unsafe scenario, improving an automated vehicle, and a computer system | |
| CN102903235B (en) | Method and device for evaluating quality of real-time road condition | |
| CN115271001B (en) | Vehicle driving condition identification method and device, vehicle and storage medium |
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 |