CN114416577A - Method and system for testing advanced driving assistance function - Google Patents

Method and system for testing advanced driving assistance function Download PDF

Info

Publication number
CN114416577A
CN114416577A CN202210079643.4A CN202210079643A CN114416577A CN 114416577 A CN114416577 A CN 114416577A CN 202210079643 A CN202210079643 A CN 202210079643A CN 114416577 A CN114416577 A CN 114416577A
Authority
CN
China
Prior art keywords
test
function
control
class function
mode
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210079643.4A
Other languages
Chinese (zh)
Inventor
彭思崴
钱诗怡
陈炯
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Weilai Automobile Technology Anhui Co Ltd
Original Assignee
Weilai Automobile Technology Anhui Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Weilai Automobile Technology Anhui Co Ltd filed Critical Weilai Automobile Technology Anhui Co Ltd
Priority to CN202210079643.4A priority Critical patent/CN114416577A/en
Publication of CN114416577A publication Critical patent/CN114416577A/en
Pending legal-status Critical Current

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
    • G06F11/3696—Methods or tools to render software testable
    • 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 invention relates to a method, a system, a computer storage medium and a computer device for testing advanced driving assistance functions. According to one aspect of the present invention, a method for testing advanced driving assistance functions including a warning-type function and a control-type function is provided, the method comprising the steps of: testing the alert class function through a first test channel and releasing the alert class function to a third test mode in response to the alert class function passing the test in the first test mode and the second test mode; and testing the control function through a second test channel, and pushing the control function to the third test mode in the first test channel to be tested simultaneously with the released warning function in response to the control function entering a second test mode through testing in a first test mode.

Description

Method and system for testing advanced driving assistance function
Technical Field
The present invention relates to the field of vehicle control, and more particularly to a method, system, computer storage medium and computer apparatus for testing advanced driving assistance functions.
Background
The advanced driving assistance system senses the surrounding environment in real time, collects data, identifies static and dynamic objects in the driving process of the vehicle by using various sensors mounted on the vehicle, and performs calculation and analysis by combining with navigator map data, so that a driver is made to perceive possible dangers in advance, and the comfort and safety of the driving process are improved.
Before the advanced driving assistance function is actually delivered for use, various test procedures such as a software simulation test, a site simulation test, an open road test and the like are generally required to fully verify the usability of the advanced driving assistance function so as to ensure that the advanced driving assistance function can meet the requirements of safety, comfort and the like.
However, in the current test and verification method, a corresponding road range needs to be deployed in each test scene, and then each algorithm is repeatedly tested for multiple times, which results in long test and verification period, high test cost and low test efficiency.
Disclosure of Invention
To solve or at least alleviate one or more of the above problems, the following technical solutions are provided.
According to a first aspect of the present invention, there is provided a method for testing advanced driving assistance functions including a warning-type function and a control-type function, the method comprising the steps of: testing the alert class function through a first test channel and releasing the alert class function to a third test mode in response to the alert class function passing the test in the first test mode and the second test mode; and testing the control function through a second test channel, and pushing the control function to the third test mode in the first test channel to be tested simultaneously with the released warning function in response to the control function entering a second test mode through testing in a first test mode.
The method for testing advanced driving assistance function according to an embodiment of the present invention, wherein in the third test mode in the first test channel: executing the released alert class function to cause a vehicle to perform an alert operation associated with the alert class function in response to the alert class function; and testing the control class function in a shadow mode.
The method for testing advanced driving assistance functionality according to an embodiment of the invention or any of the embodiments above, wherein the alert-like functionality comprises one or more of the following: the system comprises a forward collision early warning function, a backward collision early warning function, a lane departure early warning function, a blind spot collision early warning function, a door opening warning function, a parking distance warning function and a driver state monitoring function.
The method for testing advanced driving assistance functionality according to an embodiment of the invention or any of the embodiments above, wherein the control class functionality comprises one or more of the following: an automatic emergency braking function, an adaptive cruise function, a constant speed cruise function, an automatic parking function and a pedestrian emergency braking function.
The method for testing advanced driving assistance functions according to an embodiment of the invention or any of the above embodiments, wherein testing the control class function in a shadow mode comprises: operating the control-class function but not causing the vehicle to perform a control operation associated with the control-class function in response to the control-class function.
The method for testing advanced driving assistance function according to an embodiment of the invention or any of the above embodiments, wherein the method further comprises: in the third test mode in the first test channel, determining that the control class function passes a shadow mode test in response to the accuracy of the control class function reaching a preset accuracy and the recall rate of the control class function reaching a preset recall rate; in the second test mode in the second test channel, determining that the control class function passes the test in the second test mode in response to the accuracy of the control class function reaching a preset accuracy and the recall of the control class function reaching a preset recall; and determining that the control class function is validated in response to the control class function passing a shadow mode test and passing a test in the second test mode.
The method for testing advanced driving assistance functionality according to an embodiment of the invention or any of the embodiments above, wherein one or more of the following test parameters for the alert class functionality and the control class functionality are different: test duration, test scene parameters, mileage and fault tolerance.
The method for testing advanced driving assistance functionality according to an embodiment of the invention or any of the embodiments above, wherein one or more of a software-in-loop test and a hardware-in-loop test are executed in the first test mode, and a real-time test is executed in the second test mode.
The method for testing advanced driving assistance functions according to an embodiment of the invention or any of the above embodiments, wherein the step of testing the alert class function through the first test channel is performed in parallel with the step of testing the control class function through the second test channel.
According to a second aspect of the present invention, there is provided a system for testing advanced driving assistance functions including a warning-type function and a control-type function, the system comprising: a first test unit configured to test the alert class function through a first test channel and release the alert class function to a third test mode in response to the alert class function passing the test in the first test mode and the second test mode; and a second test unit configured to test the control class function through a second test channel and to push the control class function to the third test mode in the first test channel to be tested simultaneously with the released alert class function in response to the control class function entering a second test mode through testing in a first test mode.
The system for testing advanced driving assistance function according to an embodiment of the present invention, wherein the first test unit is further configured to, in the third test mode in the first test channel: executing the released alert class function to cause a vehicle to perform an alert operation associated with the alert class function in response to the alert class function; and testing the control class function in a shadow mode.
The system for testing advanced driving assistance functionality according to an embodiment of the invention or any of the embodiments above, wherein the alert-like functionality comprises one or more of the following: the system comprises a forward collision early warning function, a backward collision early warning function, a lane departure early warning function, a blind spot collision early warning function, a door opening warning function, a parking distance warning function and a driver state monitoring function.
The system for testing advanced driving assistance functionality according to an embodiment of the invention or any of the embodiments above, wherein the control class functionality comprises one or more of the following: an automatic emergency braking function, an adaptive cruise function, a constant speed cruise function, an automatic parking function and a pedestrian emergency braking function.
The system for testing advanced driving assistance functions according to an embodiment of the invention or any of the above embodiments, wherein the first testing unit is configured to test the control class function in a shadow mode by: operating the control-class function but not causing the vehicle to perform a control operation associated with the control-class function in response to the control-class function.
The system for testing advanced driving assistance function according to an embodiment of the present invention or any one of the above embodiments, wherein the first testing unit is further configured to: in the third test mode in the first test channel, determining that the control class function passes a shadow mode test in response to the accuracy of the control class function reaching a preset accuracy and the recall rate of the control class function reaching a preset recall rate; and sending a signal indicating that the control function passes the shadow mode test to the second test unit.
The system for testing advanced driving assistance function according to an embodiment of the invention or any one of the above embodiments, wherein the second testing unit is further configured to: in the second test mode in the second test channel, determining that the control class function passes the test in the second test mode in response to the accuracy of the control class function reaching a preset accuracy and the recall of the control class function reaching a preset recall; receiving the signal from the first test unit indicating that the control class function passes a shadow mode test; and determining that the control class function is validated in response to the control class function passing a shadow mode test and passing a test in the second test mode.
The system for testing advanced driving assistance functionality according to an embodiment of the invention or any of the embodiments above, wherein one or more of the following test parameters for the alert class functionality and the control class functionality are different: test duration, test scene parameters, mileage and fault tolerance.
The system for testing advanced driving assistance function according to an embodiment of the present invention or any one of the above embodiments, wherein the first test unit and the second test unit are configured to: executing one or more of a software-in-loop test and a hardware-in-loop test in the first test mode; and performing an actual vehicle test in the second test mode.
According to a third aspect of the present invention, there is provided a computer storage medium comprising instructions which, when executed, perform the steps of the method for testing advanced driving assistance functionality according to the first aspect of the present invention.
According to a fourth aspect of the present invention, there is provided a computer device comprising a memory, a processor and a computer program stored on the memory and run on the processor, the processor implementing the steps of the method for testing advanced driving assistance functions according to the first aspect of the present invention when executing the computer program.
According to the scheme for testing the advanced driving assistance function, development, deployment and test verification processes can be optimized according to requirements of different functions and performances in the test and verification processes, the control function is tested while the warning function is actually operated, accordingly, the release time of the warning function is shortened, the test cost of the control function is reduced, the function release is guaranteed to meet design specifications and safety, and meanwhile, the function test efficiency is improved.
Drawings
The above and/or other aspects and advantages of the present invention will become more apparent and more readily appreciated from the following description of the various aspects taken in conjunction with the accompanying drawings, in which like or similar elements are designated with like reference numerals. In the drawings:
fig. 1 is a flowchart of a method for testing advanced driving assistance functions according to one embodiment of the present invention.
FIG. 2 is a block diagram of a system for testing advanced driving assistance functions, according to one embodiment of the invention.
FIG. 3 is a flow diagram of a method for testing advanced driving assistance functionality according to one embodiment of the invention.
FIG. 4 is a block diagram of a computer device in accordance with one embodiment of the present invention.
Detailed Description
The following description of the specific embodiments is merely exemplary in nature and is in no way intended to limit the disclosed technology or the application and uses of the disclosed technology. Furthermore, there is no intention to be bound by any expressed or implied theory presented in the preceding technical field, background, or the following detailed description.
In the following detailed description of embodiments, numerous specific details are set forth in order to provide a more thorough understanding of the disclosed technology. It will be apparent, however, to one of ordinary skill in the art that the disclosed techniques may be practiced without these specific details. In other instances, well-known features have not been described in detail to avoid unnecessarily complicating the description.
Words such as "comprising" and "comprises" mean that, in addition to having elements or steps which are directly and explicitly stated in the description, the solution of the invention does not exclude other elements or steps which are not directly or explicitly stated. Terms such as "first" and "second" do not denote an order of the elements in time, space, size, etc., but rather are used to distinguish one element from another.
In the context of the present invention, the term "shadow mode" means that the advanced driving assistance system and various sensors on the vehicle are operating normally during manual driving, but no command is sent to the vehicle actuators to actually control the vehicle actuators.
Hereinafter, exemplary embodiments according to the present invention will be described in detail with reference to the accompanying drawings.
Fig. 1 is a flowchart of a method for testing advanced driving assistance functions according to one embodiment of the present invention.
Alternatively, the advanced driving assistance function may be divided into a warning function and a control function according to the maturity and the verification degree of the functional algorithm. It should be noted that the functional algorithm herein represents a strategic mechanism for solving the problem using advanced driving assistance methods, which can be used to calculate the control signals of the vehicle during the advanced driving assistance functional test. For example, the functional algorithms may include an automatic emergency brake algorithm for calculating brake cylinder pressure and controlling vehicle speed by brake cylinder pressure; an adaptive cruise algorithm may also be included for calculating acceleration of the vehicle and controlling the speed of the vehicle by the acceleration. Alternatively, the maturity of the functional algorithm may be determined based on an accuracy rate for indicating a probability of false positives and a recall rate for indicating a probability of false negatives.
As an example, the alert-like functions may include, but are not limited to, a forward collision warning function, a backward collision warning function, a lane departure warning function, a blind spot collision warning function, a door opening alert-like function, a parking distance warning function, a driver state monitoring function, and the like. By way of example, the control-type functions may include, but are not limited to, an automatic emergency braking function, an adaptive cruise function, a cruise control function, an automatic parking function, a pedestrian emergency braking function, and the like.
As shown in fig. 1, in step 101, an alert class function is tested by a first test channel and released to a third test mode in response to the alert class function passing the test in the first test mode and the second test mode. In step 103, the control class function is tested by the second test channel, and while entering the second test mode in response to the control class function passing the test in the first test mode, the control class function is pushed to the third test mode in the first test channel to be tested simultaneously with the released alert class function. Alternatively, step 101 and step 103 may be performed in parallel. By simultaneously testing the released warning function in the third test mode in the first test channel and the control function passing the test in the first test mode, the release time of the warning function can be shortened and the test cost of the control function can be reduced.
Optionally, in step 101, releasing the alert class function to the third test mode in response to the alert class function passing the test in the first test mode and the second test mode may include: in the first test mode, the warning function is determined to pass the test in the first test mode in response to the accuracy of the warning function reaching a preset accuracy and the recall rate of the warning function reaching a preset recall rate; in the second test mode, the warning function is determined to pass the test in the second test mode in response to the accuracy of the warning function reaching a preset accuracy and the recall rate of the warning function reaching a preset recall rate; and releasing the alert class function to a third test mode in response to determining that the alert class function passes the test in the first test mode and the second test mode.
The warning function which passes the test in the first test mode and the second test mode is released to the third test mode in time, so that the vehicle responds to the warning function to execute the warning operation associated with the warning function, the release time of the warning function can be shortened, and the safety experience of a user in an extreme scene can be improved.
Optionally, one or more of a software-in-loop test and a hardware-in-loop test may be performed in a first test mode, a real-vehicle test may be performed in a second test mode, and a real-vehicle run may be performed in a third test mode. However, the manner of testing performed in the first, second, and third test modes may be changed without departing from the spirit and scope of the present invention.
In one embodiment, a software-on-loop test may be performed in the first test mode. In the software-in-the-loop test, the consistency of the automatically generated code with the algorithm model used for code generation is verified. For example, the consistency of the automatically generated code with the algorithm model for code generation may be verified by providing the same input to the automatically generated code and the algorithm model for code generation, and comparing whether their outputs are consistent.
In another embodiment, a hardware-in-the-loop test may be performed in the first test mode. The controller system is tested in the hardware-in-loop test, and comprises hardware, bottom layer software, application layer software and the like. For example, whether the measured controller meets the design requirements is verified by connecting the measured controller with an industrial personal computer and running a model of the measured object on the industrial personal computer.
In yet another embodiment, both software-in-loop testing and hardware-in-loop testing may be performed in the first test mode.
Optionally, in the process of pushing the control-class function to the third test mode in the first test channel to be tested simultaneously with the released alert-class function, the released alert-class function is operated so that the vehicle performs an alert operation associated with the alert-class function in response to the alert-class function; and testing the control class function in a shadow mode. It should be noted that testing a control-class function in shadow mode refers to running the control-class function but not causing the vehicle to perform a control operation associated with the control-class function in response to the control-class function. Optionally, in the process of testing the control function in the shadow mode, the accuracy and the recall rate of the control function are monitored through a background, under the condition that the accuracy of the control function does not reach the preset accuracy or the recall rate of the control function does not reach the preset recall rate, a scene with false alarm (the accuracy of the control function does not reach the preset accuracy) or missed alarm (the recall rate of the control function does not reach the preset recall rate) is determined, then the scene with false alarm or missed alarm is extracted through retrieval of big data, and relevant sensor data is analyzed, so that an internal algorithm is optimized to further improve the current accuracy to the preset accuracy or improve the current recall rate to the preset recall rate.
Optionally, the alert function is pushed to a third test mode in the first test channel to be tested simultaneously with the released alert function, and the control function is determined to pass the shadow mode test in response to the accuracy of the control function reaching a preset accuracy and the recall rate of the control function reaching a preset recall rate.
Optionally, in step 101, the alert function that passes the test in the first test mode and the second test mode may be released to the third test mode in an over-the-air manner, so as to improve the release efficiency of the alert function and save the release cost of the alert function. Illustratively, the alert-like functionality that passes the test in the first test mode and the second test mode may be sent to the third test mode over the air interface of the mobile communication (e.g., by means of a text message, browser, etc.).
Optionally, in step 103, in a second test mode in the second test channel, in response to the accuracy of the control function reaching the preset accuracy and the recall rate of the control function reaching the preset recall rate, determining that the control function passes the test in the second test mode; and determining that the control class function is validated in response to the control class function passing the shadow mode test and passing the test in the second test mode.
It is understood that the preset accuracy and the preset recall rate of the warning function can be set to be less than or equal to the preset accuracy and the preset recall rate of the control function.
Optionally, different test parameters may be determined for the alert class function and the control class function for modeling the test process, which may include, but are not limited to, test duration, test scenario parameters, mileage, fault tolerance, and the like. Illustratively, the test scenario parameters may include, but are not limited to, weather parameters (e.g., sunny, cloudy, rainy, snowy, etc.), time of day parameters (e.g., early morning, daytime, evening, night, etc.), driving environment parameters (e.g., road geometry topology, roadway facility restrictions, traffic participants, etc.), and the like.
Optionally, the fault tolerance rate of the warning function test may be set to be greater than the fault tolerance rate of the control function test, the test duration of the warning function may be set to be less than the test duration of the control function, and the test mileage of the warning function may be set to be less than the test mileage of the control function. Different test parameters are determined according to the warning function and the control function, so that the release time of the warning function can be shortened, and the test efficiency is improved.
According to the method for testing the advanced driving assistance function provided by one aspect of the invention, the advanced driving assistance function can be divided into the warning function and the control function according to the maturity and the verification degree of the functional algorithm in the testing and verifying process, and the warning function and the control function are tested in parallel by using the double testing channels, so that the development, deployment and testing and verifying processes are improved. The control function is tested while the warning function is actually operated, so that the release time of the warning function is shortened, the test cost of the control function is reduced, the function test efficiency is improved while the function release is ensured to be in accordance with the design specification and safety, and the user experience of the advanced driving assistance function in the actual use process is improved.
FIG. 2 is a block diagram of a system for testing advanced driving assistance functions, according to one embodiment of the invention. Alternatively, the advanced driving assistance function may be divided into a warning function and a control function according to the maturity and the verification degree of the functional algorithm.
As shown in fig. 2, the system 200 for testing advanced driving assistance functions comprises a first test unit 201 and a second test unit 203, wherein the first test unit 201 is configured to test alert class functions through a first test channel and to release the alert class functions to a third test mode in response to the alert class functions passing the test in the first test mode and the second test mode, the second test unit 203 is configured to test control class functions through a second test channel and to push the control class functions to the third test mode in the first test channel to be tested simultaneously with the released alert class functions while the control class functions enter the second test mode through the test in the first test mode.
Optionally, the first test unit 201 may be configured to: in the first test mode, the warning function is determined to pass the test in the first test mode in response to the accuracy of the warning function reaching a preset accuracy and the recall rate of the warning function reaching a preset recall rate; in the second test mode, the warning function is determined to pass the test in the second test mode in response to the accuracy of the warning function reaching a preset accuracy and the recall rate of the warning function reaching a preset recall rate; and releasing the alert class function to a third test mode in response to determining that the alert class function passes the test in the first test mode and the second test mode.
The warning function passing the test in the first test mode and the second test mode is released to the third test mode in time, so that the vehicle responds to the warning function to execute the warning operation associated with the warning function, the release time of the warning function can be shortened, and the safety experience of a user in an extreme scene can be improved.
Alternatively, the first test unit 201 and the second test unit 203 may be configured to execute one or more of a software-in-loop test and a hardware-in-loop test in a first test mode, execute a real vehicle test in a second test mode, and execute a real vehicle run in a third test mode. However, the manner in which the first test unit 201 and the second test unit 203 perform the tests in the first test mode, the second test mode, and the third test mode may be changed without departing from the spirit and scope of the present invention.
In one embodiment, the first test unit 201 and the second test unit 203 may perform a software-in-loop test in the first test mode. In the software-in-the-loop test, the consistency of the automatically generated code with the algorithm model used for code generation is verified. For example, the consistency of the automatically generated code with the algorithm model for code generation may be verified by providing the same input to the automatically generated code and the algorithm model for code generation, and comparing whether their outputs are consistent.
In another embodiment, the first test unit 201 and the second test unit 203 may perform a hardware-in-loop test in the first test mode. The controller system is tested in the hardware-in-loop test, and comprises hardware, bottom layer software, application layer software and the like. For example, whether the measured controller meets the design requirements is verified by connecting the measured controller with an industrial personal computer and running a model of the measured object on the industrial personal computer.
In yet another embodiment, the first test unit 201 and the second test unit 203 may perform both a software-in-loop test and a hardware-in-loop test in the first test mode.
Optionally, the first test unit 201 may be configured to, in a third test mode in the first test channel: executing the released alert class function to enable the vehicle to respond to the alert class function to execute an alert operation associated with the alert class function; and testing the control class function in a shadow mode. It should be noted that testing a control-class function in shadow mode refers to running the control-class function but not causing the vehicle to perform a control operation associated with the control-class function in response to the control-class function. Optionally, in the process of testing the control function in the shadow mode, the accuracy and the recall rate of the control function are monitored through a background, under the condition that the accuracy of the control function does not reach the preset accuracy or the recall rate of the control function does not reach the preset recall rate, a scene of false report (the accuracy of the control function does not reach the preset accuracy) or missed report (the recall rate of the control function does not reach the preset recall rate) is determined to exist, then the scene of false report or missed report is extracted and relevant sensor data is analyzed through retrieval of big data, and therefore an internal algorithm is optimized to further improve the current accuracy to the preset accuracy or improve the current recall rate to the preset recall rate warning function.
Optionally, the first test unit 201 may be configured to: in a third test mode in the first test channel, determining that the control function passes the shadow mode test in response to the accuracy of the control function reaching a preset accuracy and the recall rate of the control function reaching a preset recall rate; and send a signal to the second test unit 203 indicating that the control class function passes the shadow mode test.
Optionally, the second testing unit 203 may be configured to: in a second test mode in the second test channel, determining that the control function passes the test in the second test mode in response to the accuracy of the control function reaching a preset accuracy and the recall rate of the control function reaching a preset recall rate; receiving a signal indicating that the control class function passes the shadow mode test from the first test unit 201; and determining that the control class function is validated in response to the control class function passing the shadow mode test and passing the test in the second test mode.
Optionally, the first test unit 201 may release the alert function that passes the test in the first test mode and the second test mode to the third test mode by using an over-the-air download method, so as to improve the release efficiency of the alert function and save the release cost of the alert function. Illustratively, the first test unit 201 may send the alert-like functionality that passes the test in the first test mode and the second test mode to the third test mode over an air interface of the mobile communication (e.g., by means of a text message mode, a browser mode, etc.).
It is understood that the preset accuracy and the preset recall rate of the warning function can be set to be less than or equal to the preset accuracy and the preset recall rate of the control function.
Optionally, the first testing unit 201 and the second testing unit 203 may determine different testing parameters for the warning-class function and the control-class function, respectively, for modeling the testing process, where the testing parameters may include, but are not limited to, testing duration, testing scenario parameters, mileage, fault tolerance, and the like. Illustratively, the test scenario parameters may include, but are not limited to, weather parameters (e.g., sunny, cloudy, rainy, snowy, etc.), time of day parameters (e.g., early morning, daytime, evening, night, etc.), driving environment parameters (e.g., road geometry topology, roadway facility restrictions, traffic participants, etc.), and the like.
Optionally, the fault tolerance rate of the warning function test may be set to be greater than the fault tolerance rate of the control function test, the test duration of the warning function may be set to be less than the test duration of the control function, and the test mileage of the warning function may be set to be less than the test mileage of the control function. Different test parameters are determined according to the warning function and the control function, so that the release time of the warning function can be shortened, and the test efficiency is improved.
The system for testing the advanced driving assistance function according to one aspect of the present invention can divide the advanced driving assistance function into the warning function and the control function according to the maturity and the verification degree of the functional algorithm during the testing and verification process, and test the warning function and the control function in parallel by using the dual test channels, thereby improving the development, deployment and testing and verifying processes. The control function is tested while the warning function is actually operated, so that the release time of the warning function is shortened, the test cost of the control function is reduced, the function test efficiency is improved while the function release is ensured to be in accordance with the design specification and safety, and the user experience of the advanced driving assistance function in the actual use process is improved.
FIG. 3 is a flow diagram of a method for testing advanced driving assistance functionality according to one embodiment of the invention.
Alternatively, the advanced driving assistance function may be divided into a warning function and a control function according to the maturity and the verification degree of the functional algorithm. As an example, the alert-like functions may include, but are not limited to, a forward collision warning function, a backward collision warning function, a lane departure warning function, a blind spot collision warning function, a door opening alert-like function, a parking distance warning function, a driver state monitoring function, and the like. By way of example, the control-type functions may include, but are not limited to, an automatic emergency braking function, an adaptive cruise function, a cruise control function, an automatic parking function, a pedestrian emergency braking function, and the like.
As shown in FIG. 3, steps 301, 303 and 305 show the flow of testing alert class functions by a first test channel, and steps 301 'and 303' show the flow of testing control class functions by a second test channel. Alternatively, steps 301, 303 and 305 may be performed in parallel with steps 301 'and 303'.
In step 301, the alert function is tested in the first test mode, and it is determined that the alert function passes the test in the first test mode in response to the accuracy of the alert function reaching the preset accuracy and the recall rate of the alert function reaching the preset recall rate, and then step 303 is performed.
In step 303, the alert function is tested in the second test mode, and it is determined that the alert function passes the test in the second test mode in response to the accuracy of the alert function reaching the preset accuracy and the recall rate of the alert function reaching the preset recall rate, and then step 305 is entered.
Optionally, in step 303, the warning type function that passes the test in the first test mode and the second test mode may be released to the third test mode in an over-the-air manner, so as to improve the release efficiency of the warning type function and save the release cost of the warning type function. Illustratively, the alert-like functionality that passes the test in the first test mode and the second test mode may be sent to the third test mode over the air interface of the mobile communication (e.g., by means of a text message, browser, etc.).
In step 305, the alert class function is tested in the third test mode, such that running the alert class function causes the vehicle to perform an alert operation associated with the alert class function in response to the alert class function.
Optionally, one or more of a software-in-loop test and a hardware-in-loop test may be performed in a first test mode, a real-vehicle test may be performed in a second test mode, and a real-vehicle run may be performed in a third test mode. However, the manner of testing performed in the first, second, and third test modes may be changed without departing from the spirit and scope of the present invention.
In step 301', the control class function is tested in the first test mode, and it is determined that the control class function passes the test in the first test mode in response to the accuracy of the control class function reaching the preset accuracy and the recall of the alert class function reaching the preset recall, and then step 303' is entered.
In step 303', the control class function is tested in the second test mode while the control class function is pushed to the third test mode in the first test channel to be tested simultaneously with the released alert class function.
In step 305, the control class function is tested in a shadow mode during testing of the control class function in the third test mode. It should be noted that testing a control-class function in shadow mode refers to running the control-class function but not causing the vehicle to perform a control operation associated with the control-class function in response to the control-class function. Optionally, in the process of testing the control function in the shadow mode, the accuracy and the recall rate of the control function are monitored through a background, under the condition that the accuracy of the control function does not reach the preset accuracy or the recall rate of the control function does not reach the preset recall rate, a scene of false report (the accuracy of the control function does not reach the preset accuracy) or missed report (the recall rate of the control function does not reach the preset recall rate) is determined to exist, then the scene of false report or missed report is extracted and relevant sensor data is analyzed through retrieval of big data, and therefore an internal algorithm is optimized to further improve the current accuracy to the preset accuracy or improve the current recall rate to the preset recall rate warning function.
Optionally, in step 303', it is determined that the control class function passes the test in the second test mode in response to the accuracy of the control class function reaching the preset accuracy and the recall of the control class function reaching the preset recall.
Optionally, in step 305, it is determined that the control class function passes the shadow mode test in response to the accuracy of the control class function reaching the preset accuracy and the recall of the control class function reaching the preset recall.
Optionally, the method further comprises determining that the control class function is verified in response to the control class function passing the shadow mode test and passing the test in the second test mode.
For example, the method for testing advanced driving assistance functions shown in fig. 3 may be applied to an identification function and a response function for a cone bucket, wherein the identification function for the cone bucket is an alert-type function, and the corresponding function for the cone bucket is a control-type function.
For example, the identification function of the cone bucket can be tested through the first test channel by means of steps 301, 303 and 305, and release is performed after the test is verified to be deployed to the user vehicle in advance, so that the vehicle performs a corresponding warning operation in response to the identification function of the cone bucket, such as notifying the vehicle user that the cone bucket exists in front of the vehicle through a warning signal, thereby improving the safety experience of the user in the scene that the cone bucket exists in front of the vehicle.
For example, the response function to the cone bucket may be tested by the second test channel by means of steps 301 'and 303'. In step 301', the response function to the cone bucket is tested in the first test mode, and step 303' is entered after the response function to the cone bucket passes the test in the first test mode. In step 303', the response function to the cone bucket is tested in the second test mode while the response function to the cone bucket is pushed to the third test mode in the first test channel to be tested simultaneously with the released identification function to the cone bucket. In step 305, during the period of testing the response function to the cone bucket in the third test mode, the response function to the cone bucket is tested in a shadow mode, so that the response function to the cone bucket is operated but the vehicle is not made to execute the corresponding control operation in response to the response function to the cone bucket. Meanwhile, in the process of testing the response function of the cone bucket in the shadow mode, the warning signal generated by the identification function of the cone bucket in operation is analyzed through the performance index of the background monitoring algorithm and the big data and the posterior information, so that the optimization iteration of the internal algorithm is facilitated. Further, in response to the response function to the cone-bucket passing the shadow mode test and passing the test in the second test mode, the response function to the cone-bucket is determined to be verified, at which time the response function to the cone-bucket may be applied to actual vehicle control to cause the vehicle to perform a corresponding response operation, such as early braking, in response to the response function to the cone-bucket.
The identification function and the response function of the cone barrel are tested in the mode, the response function of the cone barrel can be tested while the identification function of the cone barrel is actually operated, the release time of the identification function of the cone barrel is shortened, and the test cost of the response function of the cone barrel is reduced. Therefore, the test mode improves user experience and simultaneously realizes quick iteration and safe release of the identification function and the response function of the cone barrel.
FIG. 4 is a block diagram of a computer device in accordance with one embodiment of the present invention. As shown in fig. 4, the computer device 400 includes a memory 410, a processor 420, and a computer program 430 stored on the memory 410 and executable on the processor 420. The processor 420, when executing the computer program 430, performs the steps of a method for testing advanced driving assistance functionality according to one embodiment of the invention, such as shown in fig. 1 or fig. 3.
In addition, as described above, the present invention may also be embodied as a computer storage medium in which a program for causing a computer to execute the method for testing the advanced driving assistance function according to an aspect of the present invention is stored.
Here, as the computer storage medium, various types of computer storage media such as a disk (e.g., a magnetic disk, an optical disk, etc.), a card (e.g., a memory card, an optical card, etc.), a semiconductor memory (e.g., a ROM, a nonvolatile memory, etc.), a tape (e.g., a magnetic tape, a cassette tape, etc.), and the like can be used.
Where applicable, the various embodiments provided by the present invention can be implemented using hardware, software, or a combination of hardware and software. Also, where applicable, the various hardware components and/or software components set forth herein may be combined into composite components comprising software, hardware, and/or both without departing from the scope of the present disclosure. Where applicable, the various hardware components and/or software components set forth herein may be separated into sub-components comprising software, hardware, or both without departing from the scope of the present invention. Further, where applicable, it is contemplated that software components may be implemented as hardware components, and vice versa.
Software, such as program code and/or data, according to the present invention can be stored on one or more computer storage media. It is also contemplated that the software identified herein may be implemented using one or more general purpose or special purpose computers and/or computer systems that are networked and/or otherwise. Where applicable, the order of various steps described herein may be changed, combined into composite steps, and/or separated into sub-steps to provide features described herein.
The embodiments and examples set forth herein are presented to best explain embodiments in accordance with the invention and its particular application and to thereby enable those skilled in the art to make and utilize the invention. However, those skilled in the art will recognize that the foregoing description and examples have been presented for the purpose of illustration and example only. The description as set forth is not intended to cover all aspects of the invention or to limit the invention to the precise form disclosed.

Claims (10)

1. A method for testing advanced driving assistance functions, wherein the advanced driving assistance functions include a warning-type function and a control-type function, the method comprising the steps of:
testing the alert class function through a first test channel and releasing the alert class function to a third test mode in response to the alert class function passing the test in the first test mode and the second test mode; and
testing the control class function through a second test channel and pushing the control class function to the third test mode in the first test channel to be tested simultaneously with the released alert class function in response to the control class function entering a second test mode through testing in a first test mode,
wherein one or more of the following test parameters for the alert class function and the control class function are different: test duration, test scenario parameters, mileage, fault tolerance,
wherein one or more of a software-in-loop test and a hardware-in-loop test are executed in the first test mode, and an actual vehicle test is executed in the second test mode,
wherein the step of testing the alert-type function through the first test channel is performed in parallel with the step of testing the control-type function through the second test channel.
2. The method of claim 1, wherein in the third test mode in the first test channel:
executing the released alert class function to cause a vehicle to perform an alert operation associated with the alert class function in response to the alert class function; and
testing the control class function in shadow mode, wherein testing the control class function in shadow mode comprises running the control class function but not causing a vehicle to perform a control operation associated with the control class function in response to the control class function.
3. The method of claim 1, wherein the alert class function comprises one or more of: a forward collision early warning function, a backward collision early warning function, a lane departure early warning function, a blind spot collision early warning function, a door opening warning function, a parking distance warning function and a driver state monitoring function;
wherein the control class functions include one or more of: an automatic emergency braking function, an adaptive cruise function, a constant speed cruise function, an automatic parking function and a pedestrian emergency braking function.
4. The method of claim 2, wherein the method further comprises:
in the third test mode in the first test channel, determining that the control class function passes a shadow mode test in response to the accuracy of the control class function reaching a preset accuracy and the recall rate of the control class function reaching a preset recall rate;
in the second test mode in the second test channel, determining that the control class function passes the test in the second test mode in response to the accuracy of the control class function reaching a preset accuracy and the recall of the control class function reaching a preset recall; and
determining that the control class function is validated in response to the control class function passing a shadow mode test and passing a test in the second test mode.
5. A system for testing advanced driving assistance functions, the advanced driving assistance functions including a warning-type function and a control-type function, the system comprising:
a first test unit configured to test the alert class function through a first test channel and release the alert class function to a third test mode in response to the alert class function passing the test in the first test mode and the second test mode; and
a second test unit configured to test the control class function through a second test channel and to push the control class function to the third test mode in the first test channel to be tested simultaneously with the released alert class function in response to the control class function entering a second test mode through testing in a first test mode,
wherein one or more of the following test parameters for the alert class function and the control class function are different: test duration, test scenario parameters, mileage, fault tolerance,
wherein the first test unit and the second test unit are configured to: executing one or more of a software-in-loop test and a hardware-in-loop test in the first test mode; and performing an actual vehicle test in the second test mode.
6. The system of claim 5, wherein the first test unit is further configured to, in the third test mode in the first test channel:
executing the released alert class function to cause a vehicle to perform an alert operation associated with the alert class function in response to the alert class function; and
testing the control-class function in a shadow mode such that the control-class function is executed but such that the vehicle is not responsive to the control-class function to perform a control operation associated with the control-class function.
7. The system of claim 5, wherein the alert class function comprises one or more of: a forward collision warning function, a backward collision warning function, a lane departure warning function, a blind spot collision warning function, a door opening warning function, a parking distance warning function, and a driver state monitoring function,
wherein the control class functions include one or more of: an automatic emergency braking function, an adaptive cruise function, a constant speed cruise function, an automatic parking function and a pedestrian emergency braking function.
8. The system of claim 6, wherein the first test unit is further configured to:
in the third test mode in the first test channel, determining that the control class function passes a shadow mode test in response to the accuracy of the control class function reaching a preset accuracy and the recall rate of the control class function reaching a preset recall rate; and
sending a signal to the second test unit indicating that the control class function passes a shadow mode test,
wherein the second test unit is further configured to:
in the second test mode in the second test channel, determining that the control class function passes the test in the second test mode in response to the accuracy of the control class function reaching a preset accuracy and the recall of the control class function reaching a preset recall;
receiving the signal from the first test unit indicating that the control class function passes a shadow mode test; and
determining that the control class function is validated in response to the control class function passing a shadow mode test and passing a test in the second test mode.
9. A computer storage medium comprising instructions that, when executed, perform the method of any of claims 1-4.
10. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements the method of any one of claims 1 to 4.
CN202210079643.4A 2022-01-24 2022-01-24 Method and system for testing advanced driving assistance function Pending CN114416577A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210079643.4A CN114416577A (en) 2022-01-24 2022-01-24 Method and system for testing advanced driving assistance function

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210079643.4A CN114416577A (en) 2022-01-24 2022-01-24 Method and system for testing advanced driving assistance function

Publications (1)

Publication Number Publication Date
CN114416577A true CN114416577A (en) 2022-04-29

Family

ID=81276516

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210079643.4A Pending CN114416577A (en) 2022-01-24 2022-01-24 Method and system for testing advanced driving assistance function

Country Status (1)

Country Link
CN (1) CN114416577A (en)

Similar Documents

Publication Publication Date Title
CN111006879B (en) Port environment-oriented man-machine hybrid driving automatic driving test method and test platform thereof
CN110570538B (en) Method, device and equipment for managing black box data in intelligent driving automobile
US10632985B2 (en) Hybrid vehicle and method of predicting driving pattern in the same
US9840254B2 (en) Method and system for adaptive detection and application of horn for an autonomous vehicle
Nilsson et al. Safe transitions from automated to manual driving using driver controllability estimation
CN106627579A (en) Coordination test in vehicle queue
JP2018203250A5 (en)
CN107015550B (en) Diagnostic test execution control system and method
US10023164B2 (en) Validating automotive safety functions
US10629008B2 (en) Vehicle diagnostic operation
US10654467B2 (en) Hybrid vehicle and method of performing temperature control therefor
US10755565B2 (en) Prioritized vehicle messaging
RU2678416C2 (en) Cruise control system of vehicle and method for operation thereof
US20210264213A1 (en) Neural network for localization and object detection
CN114489004B (en) Unmanned test method and system thereof
US11657635B2 (en) Measuring confidence in deep neural networks
CN114416577A (en) Method and system for testing advanced driving assistance function
US11584383B2 (en) Vehicle feature availability detection
CN114913620A (en) Data extraction method and device, computer equipment and storage medium
CN115346288A (en) Simulation driving record acquisition method and system, electronic equipment and storage medium
JP7426295B2 (en) Control equipment, programs and systems
US20230339517A1 (en) Autonomous driving evaluation system
Khan Design of real-time transition from driving assistance to automation function: Bayesian artificial intelligence approach
US20210089044A1 (en) Method for controlling a motor vehicle remotely
US20210209381A1 (en) Temporal cnn rear impact alert system

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