Calibration method, device, electronic device and storage medium for autonomous driving algorithm

Abstract

The present application relates to the field of algorithm calibration technology, and more particularly to a calibration method, apparatus, electronic device, and storage medium for an autonomous driving algorithm, wherein the method comprises: reading a configuration file under a target path based on a preset configuration file class and obtaining configuration information of the configuration file; generating a target database based on the configuration information and obtaining calibratable variables to be modified, numerical values ​​corresponding to the calibratable variables to be modified, and types of the calibratable variables to be modified; locating the calibratable variables to be modified from the target database, and modifying the calibratable variables to be modified in the target database according to the numerical values ​​corresponding to the calibratable variables to be modified and the types of the calibratable variables to be modified, thereby obtaining calibration results for the autonomous driving algorithm. The embodiments of the present application modify the values ​​of global variables in the current program, thereby enabling multiple consecutive calibrations with only one compilation, optimizing the calibration process, and ultimately achieving an efficient and flexible calibration effect.

Description

Technical Field

[0001] The present application relates to the technical field of algorithm calibration, and in particular to a calibration method, device, electronic device and storage medium for an autonomous driving algorithm. Background Art

[0002] With the vigorous development of autonomous driving technology, algorithm calibration technology also needs to adapt to the current development and speed of autonomous driving. Therefore, efficient and flexible calibration is very important to improve the efficiency of autonomous driving algorithms.

[0003] In related technologies, most algorithm calibration methods are to calibrate the algorithm by modifying the code.

[0004] However, this approach often requires recompiling the calibration of the algorithm module, that is, each calibration requires compiling the existing code again, which makes the calibration method inflexible and inefficient, and difficult to adapt to the current rapid development rhythm and speed, which needs to be solved urgently. Summary of the Invention

[0005] The present application provides a calibration method, device, vehicle and storage medium for an autonomous driving algorithm to solve the problem in related technologies that algorithm calibration requires multiple compilation of algorithm modules.

[0006] The first aspect of the present application provides a calibration method for an autonomous driving algorithm, comprising the following steps: based on a preset configuration file class, reading a configuration file under a target path and obtaining configuration information of the configuration file; generating a target database based on the configuration information, and obtaining a calibratable variable to be modified, a numerical value corresponding to the calibratable variable to be modified, and a type of the calibratable variable to be modified; and locating the calibratable variable to be modified from the target database, and modifying the calibratable variable to be modified in the target database according to the numerical value corresponding to the calibratable variable to be modified and the type of the calibratable variable to be modified, to obtain a calibration result of the autonomous driving algorithm.

[0007] According to the above technical means, by modifying the values ​​of global variables in the target database, an efficient and flexible calibration effect is achieved.

[0008] Furthermore, in one embodiment of the present application, before reading the configuration file under the target path based on the preset configuration file class and obtaining the configuration information of the configuration file, it also includes: traversing all files under the target path to obtain multiple calibrable variables of the autonomous driving algorithm, the type of each calibrable variable and the numerical value corresponding to each calibrable variable; generating the configuration file and the preset configuration file class based on the multiple calibrable variables, the type of each calibrable variable and the numerical value corresponding to each calibrable variable.

[0009] According to the above technical means, by traversing the calibrable variables, the type of each calibrable variable and the numerical value corresponding to each calibrable variable, a configuration file containing scalable variables and the code required for calibration can be generated.

[0010] Furthermore, in one embodiment of the present application, traversing all files under the target path to obtain multiple calibrable variables of the autonomous driving algorithm, the type of each calibrable variable and the numerical value corresponding to each calibrable variable includes: traversing all files under the target path, and obtaining multiple header files through preset file names, and based on a preset regular matching algorithm, matching the multiple calibrable variables and the type of each calibrable variable from the multiple header files; based on the multiple header files, traversing all files under the target path to obtain multiple source files, and based on the preset regular matching algorithm, matching the numerical value corresponding to each calibrable variable from the multiple source files.

[0011] According to the above technical means, all global variables and corresponding types are found by traversing each file and using regular matching methods, so as to perform calibration, thereby improving the accuracy of the calibration results.

[0012] Furthermore, in an embodiment of the present application, after the target database is generated based on the configuration information, the method further includes: importing the target database into a preset visualization window to modify the target database through the preset visualization window.

[0013] According to the above technical means, a series of problems caused by modifying the configuration file can be reduced by modifying the target database through the visual window.

[0014] The second aspect of the present application provides a calibration device for an autonomous driving algorithm, including: a first acquisition module, used to read the configuration file under the target path based on a preset configuration file class, and obtain the configuration information of the configuration file; a second acquisition module, used to generate a target database based on the configuration information, and obtain the calibrable variables to be modified, the numerical values ​​corresponding to the calibrable variables to be modified, and the types of the calibrable variables to be modified; and a revision module, used to locate the calibrable variables to be modified from the target database, and modify the calibrable variables to be modified in the target database according to the numerical values ​​corresponding to the calibrable variables to be modified and the types of the calibrable variables to be modified, so as to obtain the calibration results of the autonomous driving algorithm.

[0015] Furthermore, in one embodiment of the present application, before reading the configuration file under the target path based on the preset configuration file class and obtaining the configuration information of the configuration file, the first acquisition module also includes: a traversal unit, used to traverse all files under the target path to obtain multiple calibrable variables of the autonomous driving algorithm, the type of each calibrable variable and the numerical value corresponding to each calibrable variable; a generation unit, used to generate the configuration file and the preset configuration file class based on the multiple calibrable variables, the type of each calibrable variable and the numerical value corresponding to each calibrable variable.

[0016] Furthermore, in one embodiment of the present application, the traversal unit is specifically used to: traverse all files under the target path, and obtain multiple header files through preset file names, and based on a preset regular matching algorithm, match the multiple calibrable variables and the type of each calibrable variable from the multiple header files; based on the multiple header files, traverse all files under the target path to obtain multiple source files, and based on the preset regular matching algorithm, match the numerical value corresponding to each calibrable variable from the multiple source files.

[0017] Furthermore, in one embodiment of the present application, after generating the target database based on the configuration information, the second acquisition module is further configured to: import the target database into a preset visualization window to modify the target database through the preset visualization window.

[0018] The third aspect of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to implement the calibration method of the autonomous driving algorithm as described in the above embodiment.

[0019] The fourth aspect of the present application provides a computer-readable storage medium on which a computer program is stored. The program is executed by a processor to implement the calibration method of the autonomous driving algorithm as described in the above embodiment.

[0020] Based on a preset configuration file class, this embodiment of the application reads the configuration file under the target path and obtains the corresponding configuration information, thereby generating a target database, obtaining the calibratable variables to be modified and their corresponding values ​​and types, and then locating the calibratable variables to be modified from the target database. The calibratable variables to be modified in the target database are modified according to their corresponding values ​​and types, thereby obtaining the calibration results of the autonomous driving algorithm. This solves the problem of requiring multiple compilations of algorithm modules to achieve algorithm calibration in related technologies.

[0021] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0023] Figure 1 This is a flowchart of a calibration method for an autonomous driving algorithm provided in accordance with an embodiment of the present application;

[0024] Figure 2 This is an overall calibration flow chart according to one embodiment of the present application;

[0025] Figure 3 A schematic diagram of a visualization interface according to an embodiment of the present application;

[0026] Figure 4 1 is a block diagram of a calibration device for an autonomous driving algorithm according to an embodiment of the present application;

[0027] Figure 5 Schematic diagram of the structure of an electronic device according to an embodiment of the present application.

[0028] Explanation of the reference numerals: 10 - calibration device for the autonomous driving algorithm; 100 - first acquisition module, 200 - second acquisition module, 300 - revision module. DETAILED DESCRIPTION

[0029] The following describes in detail embodiments of the present application. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0030] The following describes, with reference to the accompanying drawings, a calibration method, apparatus, electronic device, and storage medium for an autonomous driving algorithm according to an embodiment of the present application. In response to the problem mentioned in the background art above that algorithm calibration requires multiple compilations of algorithm modules, the present application provides a calibration method for an autonomous driving algorithm. In this method, based on a preset configuration file class, a configuration file under a target path is read and corresponding configuration information is obtained, thereby generating a target database. The calibratable variables to be modified and their corresponding values ​​and types are then obtained. The calibratable variables to be modified are then located from the target database and modified in the target database according to their corresponding values ​​and types, resulting in a calibration result for the autonomous driving algorithm. By modifying the values ​​of global variables in the current program, multiple calibrations can be performed continuously with only one compilation, thus optimizing the calibration process and ultimately achieving an efficient and flexible calibration effect. This solves the problem of the need to compile algorithm modules multiple times in the related art to achieve algorithm calibration.

[0031] Specifically, the embodiment of the present application is to realize flexible calibration of autonomous driving algorithms. The calibration method can be divided into two parts: the first part is to identify calibrable quantities and automatically generate corresponding codes and configuration files; the second part is a visual interface for modifying configuration files. These two methods will be discussed in detail through specific embodiments below.

[0032] Figure 1 A flowchart of a calibration method for an autonomous driving algorithm provided in an embodiment of the present application.

[0033] like Figure 1 As shown, the calibration method of the autonomous driving algorithm includes the following steps:

[0034] In step S101, based on a preset configuration file class, the configuration file in the target path is read, and configuration information of the configuration file is obtained.

[0035] Among them, the preset configuration file class can automatically modify the corresponding configuration information by reading the configuration file under the target path. That is to say, if the configuration file is modified, the configuration file class will modify the value of the corresponding calibration amount to achieve the purpose of calibration.

[0036] Furthermore, in one embodiment of the present application, before reading the configuration file under the target path based on the preset configuration file class and obtaining the configuration information of the configuration file, it also includes: traversing all files under the target path to obtain multiple calibrable variables of the autonomous driving algorithm, the type of each calibrable variable and the numerical value corresponding to each calibrable variable; generating a configuration file and a preset configuration file class based on the multiple calibrable variables, the type of each calibrable variable and the numerical value corresponding to each calibrable variable.

[0037] Furthermore, in one embodiment of the present application, all files under the target path are traversed to obtain multiple calibrable variables of the autonomous driving algorithm, the type of each calibrable variable, and the numerical value corresponding to each calibrable variable, including: traversing all files under the target path, and obtaining multiple header files through preset file names, and based on a preset regular matching algorithm, matching multiple calibrable variables and the type of each calibrable variable from the multiple header files; based on the multiple header files, traversing all files under the target path to obtain multiple source files, and based on the preset regular matching algorithm, matching the numerical value corresponding to each calibrable variable from the multiple source files.

[0038] Among them, there are many preset file names, such as yaml, xml, jason, etc. Preferably, the embodiment of the present application uses jason as the file name, so as to achieve the functions of easy reading, writing, machine parsing and generation.

[0039] Specifically, if Figure 2 As shown, in order to achieve the above calibration purpose, before this, first, it is necessary to traverse all files under the target path and obtain multiple header files through the file name. When opening each file, based on the regular matching algorithm, multiple global variables and corresponding types are matched from multiple header files, that is, the calibrable variables and the type of each calibrable variable are matched; secondly, based on the obtained multiple header files, all files under the current target path are traversed again to obtain multiple source files, and based on the regular matching algorithm, the values ​​corresponding to each calibrable variable are matched from multiple source files; finally, based on the multiple calibrable variables, the type of each calibrable variable and the value corresponding to each calibrable variable, a configuration file is generated, and a configuration file class is generated by reading the configuration file, and instantiated in the main program of the algorithm program, so that the flexible calibration function can be realized by compiling and running the algorithm module once. Among them, the content of the configuration file is the variable name of the calibrable quantity, the type of each calibrable variable and the value corresponding to each calibrable variable.

[0040] In step S102 , a target database is generated based on the configuration information, and the calibratable variables to be modified, the values ​​corresponding to the calibratable variables to be modified, and the types of the calibratable variables to be modified are obtained.

[0041] Furthermore, in one embodiment of the present application, after the target database is generated based on the configuration information, the method further includes: importing the target database into a preset visualization window to modify the target database through the preset visualization window.

[0042] The preset visualization window may be in any form. The visualization window in the embodiment of the present application is a user-specified window to reduce a series of problems that may arise from modifying the configuration file.

[0043] Specifically, after opening an executable program in a visualization window, the embodiment of the present application will first automatically read the value of the configuration file under the current path and obtain the configuration information of the configuration file, generate a target database through the configuration information of the configuration file, and obtain the calibrable variables to be modified, the numerical values ​​corresponding to the calibrable variables to be modified, and the types of the calibrable variables to be modified; secondly, the data in the obtained target database is imported into the visualization window to modify the target database through the visualization window.

[0044] In step S103, the calibratable variable to be modified is located from the target database, and the calibratable variable to be modified in the target database is modified according to the numerical value corresponding to the calibratable variable to be modified and the type of the calibratable variable to be modified, so as to obtain the calibration result of the autonomous driving algorithm.

[0045] Specifically, if Figure 3 As shown, after the data obtained from the target database is imported into the visualization window, the embodiment of the present application can find all the calibrable quantities to be modified in the "Signal Name". Select the value of any calibrable quantity to be modified, modify the value, and then click OK to modify the value in the configuration file, thereby obtaining the calibration result of the autonomous driving algorithm. Among them, "Signal Name" supports a drop-down selection, and you can click the desired calibration quantity in the drop-down menu. At the same time, "Signal Name" also supports a fuzzy search selection method. In this way, the configuration file can be modified and only the window specified by the user is opened to ensure that when modifying the configuration file, calibration will not be impossible due to errors in the format of the configuration file, thereby reducing a series of problems caused by modifying the configuration file.

[0046] According to the calibration method of the autonomous driving algorithm of the embodiment of the present application, based on a preset configuration file class, the configuration file under the target path is read and the corresponding configuration information is obtained, thereby generating a target database, obtaining the calibratable variables to be modified and their corresponding values ​​and types, then locating the calibratable variables to be modified from the target database, and modifying the calibratable variables to be modified in the target database according to their corresponding values ​​and types, to obtain the calibration results of the autonomous driving algorithm. By modifying the values ​​of global variables in the current program, multiple continuous calibrations can be achieved with only one compilation, thus optimizing the calibration process and ultimately achieving efficient and flexible calibration results. This solves the problem of requiring multiple compilations of algorithm modules to achieve algorithm calibration in related technologies.

[0047] Next, the calibration device of the autonomous driving algorithm proposed in the embodiment of the present application is described with reference to the accompanying drawings.

[0048] Figure 4 It is a block diagram of a calibration device for an autonomous driving algorithm according to an embodiment of the present application.

[0049] like Figure 4 As shown, the calibration device 10 of the autonomous driving algorithm includes: a first acquisition module 100, a second acquisition module 200 and a revision module 300.

[0050] The first acquisition module 100 is configured to read the configuration file under the target path based on a preset configuration file class and obtain configuration information of the configuration file;

[0051] A second acquisition module 200 is configured to generate a target database based on the configuration information, and acquire the calibratable variable to be modified, the value corresponding to the calibratable variable to be modified, and the type of the calibratable variable to be modified; and

[0052] The revision module 300 is used to locate the calibratable variables to be modified from the target database, and modify the calibratable variables to be modified in the target database according to the numerical values ​​corresponding to the calibratable variables to be modified and the types of the calibratable variables to be modified, so as to obtain the calibration results of the autonomous driving algorithm.

[0053] Furthermore, in one embodiment of the present application, before reading the configuration file under the target path based on the preset configuration file class and obtaining the configuration information of the configuration file, the first obtaining module 100 further includes: a traversal unit and a generation unit.

[0054] The traversal unit is used to traverse all files under the target path to obtain multiple calibrable variables of the autonomous driving algorithm, the type of each calibrable variable, and the value corresponding to each calibrable variable;

[0055] The generating unit is used to generate a configuration file and a preset configuration file class based on a plurality of calibratable variables, a type of each calibratable variable and a numerical value corresponding to each calibratable variable.

[0056] Furthermore, in one embodiment of the present application, the traversal unit is specifically configured to:

[0057] Traverse all files under the target path, obtain multiple header files through the preset file name, and match multiple calibrable variables and the type of each calibrable variable from the multiple header files based on the preset regular matching algorithm;

[0058] Based on multiple header files, all files under the target path are traversed to obtain multiple source files, and based on the preset regular matching algorithm, the numerical value corresponding to each calibrable variable is matched from the multiple source files.

[0059] Furthermore, in one embodiment of the present application, after generating the target database based on the configuration information, the second acquisition module 200 is further configured to:

[0060] Import the target database into the preset visualization window to modify the target database through the preset visualization window.

[0061] According to the calibration device for the autonomous driving algorithm of the embodiment of the present application, based on a preset configuration file class, the device reads the configuration file under the target path and obtains the corresponding configuration information, thereby generating a target database and obtaining the calibratable variables to be modified and their corresponding values ​​and types. The device then locates the calibratable variables to be modified from the target database and modifies the calibratable variables to be modified in the target database according to their corresponding values ​​and types, thereby obtaining the calibration results of the autonomous driving algorithm. By modifying the values ​​of global variables in the current program, multiple consecutive calibrations can be achieved with just one compilation, thus optimizing the calibration process and ultimately achieving an efficient and flexible calibration effect. This solves the problem in the related art of requiring multiple compilations of algorithm modules to achieve algorithm calibration.

[0062] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include:

[0063] Memory 501 , processor 502 , and computer programs stored in the memory 501 and executable on the processor 502 .

[0064] When the processor 502 executes the program, the calibration method of the autonomous driving algorithm provided in the above embodiment is implemented.

[0065] Furthermore, the electronic device further includes:

[0066] The communication interface 503 is used for communication between the memory 501 and the processor 502 .

[0067] The memory 501 is used to store computer programs that can be run on the processor 502 .

[0068] The memory 501 may include a high-speed RAM (Random Access Memory) memory, and may also include a non-volatile memory, such as at least one disk memory.

[0069] If the memory 501, the processor 502, and the communication interface 503 are implemented independently, the communication interface 503, the memory 501, and the processor 502 can be connected to each other via a bus and communicate with each other. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0070] Optionally, in a specific implementation, if the memory 501, the processor 502 and the communication interface 503 are integrated on a chip, the memory 501, the processor 502 and the communication interface 503 can communicate with each other through an internal interface.

[0071] The processor 502 may be a CPU (Central Processing Unit), or an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application.

[0072] An embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the calibration method of the autonomous driving algorithm as described above is implemented.

[0073] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0074] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of technical features indicated. Thus, a feature specified as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of this application, "N" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0075] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application belong.

[0076] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiment, the N steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array, a field programmable gate array, etc.

[0077] Those skilled in the art will appreciate that all or part of the steps in the method for implementing the above-mentioned embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0078] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A calibration method for an autonomous driving algorithm, characterized in that: The following steps are involved: Traversing all files under the target path, obtaining multiple header files through a preset file name, and matching multiple calibratable variables and the type of each calibratable variable from the multiple header files based on a preset regular matching algorithm; Based on the multiple header files, traverse all files under the target path to obtain multiple source files, and based on the preset regular matching algorithm, match the multiple source files to obtain the value corresponding to each calibratable variable; generating a configuration file and a preset configuration file class based on the plurality of calibratable variables, a type of each calibratable variable, and a numerical value corresponding to each calibratable variable; Based on the preset configuration file class, read the configuration file under the target path and obtain the configuration information of the configuration file; Generate a target database based on the configuration information, and obtain a calibratable variable to be modified, a numerical value corresponding to the calibratable variable to be modified, and a type of the calibratable variable to be modified; as well as The calibratable variable to be modified is located from the target database, and the calibratable variable to be modified in the target database is modified according to the numerical value corresponding to the calibratable variable to be modified and the type of the calibratable variable to be modified, so as to obtain a calibration result of the autonomous driving algorithm.

2. The method according to claim 1, characterized in that After generating the target database based on the configuration information, the method further includes: The target database is imported into a preset visualization window, so as to modify the target database through the preset visualization window.

3. A calibration device for an autonomous driving algorithm, characterized in that: include: A traversal unit, configured to traverse all files under a target path, obtain multiple header files by using a preset file name, and obtain multiple calibratable variables and the type of each calibratable variable from the multiple header files based on a preset regular matching algorithm; Based on the multiple header files, traverse all files under the target path to obtain multiple source files, and based on the preset regular matching algorithm, match the multiple source files to obtain the value corresponding to each calibratable variable; a generating unit, configured to generate a configuration file and a preset configuration file class based on the plurality of calibratable variables, a type of each calibratable variable, and a numerical value corresponding to each calibratable variable; A first acquisition module is used to read the configuration file under the target path based on a preset configuration file class and obtain configuration information of the configuration file; a second acquisition module, configured to generate a target database based on the configuration information, and acquire a calibratable variable to be modified, a value corresponding to the calibratable variable to be modified, and a type of the calibratable variable to be modified; as well as A revision module is used to locate the calibratable variable to be modified from the target database, and modify the calibratable variable to be modified in the target database according to the numerical value corresponding to the calibratable variable to be modified and the type of the calibratable variable to be modified, so as to obtain a calibration result of the autonomous driving algorithm.

4. The device according to claim 3, characterized in that After generating the target database based on the configuration information, the second acquisition module is further configured to: The target database is imported into a preset visualization window, so as to modify the target database through the preset visualization window.

5. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the calibration method for the autonomous driving algorithm as claimed in claim 1 or 2.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the calibration method of the autonomous driving algorithm as described in claim 1 or 2.

Images