KR20200054370A - Apparatus and method for automatically calibrating integrated sensor of autonomous vehicle - Google Patents

Abstract

Suggested are a device and a method for automatically correcting an integrated sensor of an autonomous vehicle to automatically correct output data of a LIDAR of an integrated sensor in an autonomous vehicle having an integrated sensor in which a camera and a LIDAR are integrally installed. The suggested device includes a sensor fusion unit connected to an integrated sensor in which a camera and a LIDAR are integrated, generating a correction value based on a reference camera image of the camera and a reference LIDAR image of the LIDAR, and automatically correcting output data of the LIDAR with the correction value.

Description

Apparatus and method for automatically calibrating integrated sensor of autonomous vehicle

The present invention relates to an automatic sensor autocorrecting device and method for an autonomous driving vehicle, and more specifically, to enable automatic correction of an integrated sensor in an autonomous vehicle with an integrated sensor in which a camera and a lidar are installed. It relates to a device and method.

In general, an autonomous vehicle is a vehicle that drives itself without the driver having to operate the vehicle, and refers to a vehicle that automatically drives the vehicle by grasping the road condition without controlling the brake, handle, or accelerator pedal.

As a core technology for smart car implementation, for autonomous vehicles, highway driving support systems (HDA, technology that automatically maintains the distance between cars), as well as rear-side warning systems (BSD, detects nearby vehicles during reversing and sounds an alarm) Technology), automatic emergency braking system (AEB, technology to start the braking system when the vehicle in front is not recognized), lane departure warning system (LDWS), lane maintenance support system (LKAS, technology to compensate for leaving the lane without a turn signal) , Advanced Smart Cruise Control (ASCC, a technology that maintains a constant distance between cars at a set speed and constant speed driving), a congestion section driving support system (TJA), etc. should be implemented.

Cameras are used in various systems for such self-driving vehicles, but it is difficult to measure the distance of an object because the accuracy of distance information is reduced only by the camera.

In addition, the camera has characteristic limitations on environmental factors such as illumination and weather.

Accordingly, LiDAR may be used in parallel to compensate for the characteristic limitations of the camera itself.

However, the camera and the rider differ in viewing angle. Due to this difference in viewing angle, a separate correction operation is required according to the installation location.

In particular, even if mechanical correction is performed according to the difference in viewing angle between the camera and the lidar in the production process, the mechanical correction may be sold inaccurately due to operator shaking.

In addition, even if the mechanical correction by the operator has been normally performed, the camera and the lidar may be slightly displaced in place when the integrated sensor integrated with the camera and the lidar is mounted on an autonomous vehicle and used for a long time.

Prior Art 1: Republic of Korea Patent Publication No. 10-2018-0055292 (Multi-LIDAR coordinate system integration method) Prior art 2: Republic of Korea Patent Publication No. 10-2014-0065627 (vehicle camera calibration device and method) Prior art 3: Republic of Korea Patent Publication No. 10-2015-0142543 (integrated sensor system for automobiles) Prior art 4: Republic of Korea Patent Publication No. 10-2015-0066182 (precision positioning device and method)

The present invention has been proposed to solve the above-described conventional problems, autonomous to enable automatic correction of the output data of the lidar of the integrated sensor in an autonomous vehicle with an integrated sensor in which a camera and a lidar are integrated. An object of the present invention is to provide an apparatus and method for automatically calibrating an integrated sensor of a driving vehicle.

In order to achieve the above object, the automatic sensor autocorrecting device of the autonomous vehicle according to the preferred embodiment of the present invention is connected to an integrated sensor in which a camera and a lidar are integrated, and the reference camera image and the lidar of the camera. It includes; a sensor fusion unit for generating a correction value based on the reference lidar image, and automatically correcting the output data of the lidar with the correction value.

The sensor fusion unit compares the reference camera image and the reference lidar image to calculate deviation values for the x-axis, y-axis, and z-axis, and corrects the x-axis, y-axis, and z-axis with the calculated deviation values. You can create a value.

The sensor fusion unit may output a notification message to the display unit that mechanical correction is necessary when the generated correction value exceeds a predetermined range.

The sensor fusion unit may output a correction value exceeding the preset range.

The sensor fusion unit controls the automatic correction operation based on the generation of the correction value and the generated correction value, and places a plurality of first markers on the reference camera image, and a plurality of second values on the reference lidar image. A control unit for placing a marker; A marker recognition unit recognizing the first marker and the second marker; A marker information extraction unit extracting information of the recognized first marker and information of the second marker; A correction value generation unit comparing the information of the first marker and the information of the second marker to calculate a deviation value between each other, and generating a correction value based on the deviation value; And an automatic correction unit that outputs the corrected data by applying the correction value to the output data of the rider received after generating the correction value.

The control unit may output, to the display unit, a notification message that mechanical correction is necessary when the generated correction value exceeds a preset range.

The control unit may output a correction value exceeding the preset range.

The information of the first marker and the information of the second marker may be x, y, and z-axis coordinate values of the vertices of each marker.

On the other hand, the method for automatically calibrating the integrated sensor of the autonomous vehicle according to the preferred embodiment of the present invention is an integrated sensor automatic calibration method in the integrated sensor automatic calibrating device for the autonomous vehicle, in the integrated sensor integrated with the camera and the lidar. Generating a correction value based on a reference camera image of the camera and a reference lidar image of the lidar; And automatically correcting the output data of the lidar with the generated correction value.

The generating of the correction value may include calculating a deviation value for the x-axis, y-axis, and z-axis by comparing the reference camera image and the reference lidar image; And generating correction values for the x-axis, y-axis, and z-axis with the calculated deviation value.

The calculating of the deviation value may recognize the first marker from the reference camera image in which a plurality of first markers are disposed, and recognize the second marker in the reference lidar image in which a plurality of second markers are disposed. To do; Extracting information of the recognized first marker and information of the second marker; And comparing the extracted information of the first marker and the information of the second marker to calculate a deviation value between each other.

The first marker and the second marker are the same number of each other, and the extraction step includes the x, y, z axis coordinate values of the vertex of the first marker and the x, y, z axis coordinates of the vertex of the second marker. Each value can be obtained.

In the calculating of the mutual deviation value, the coordinate values of respective vertices of the markers corresponding to each other between the first marker and the second marker may be compared with each other to calculate deviations between the vertices corresponding to each other.

Between the step of generating the correction value and the step of automatically correcting, if the generated correction value exceeds a predetermined range, displaying a message indicating that mechanical correction is necessary on the display unit. .

According to the present invention of such a configuration, in an autonomous vehicle having an integrated sensor in which a camera and a lidar are integrally installed, the camera data and the lidar data of the integrated sensor are mutually compared to generate a correction value, and the generated correction value By applying to the point cloud data of the lidar after generating the correction value, the lidar data can be automatically corrected (fine correction).

1 is a view for explaining an automatic sensor automatic correction device of an autonomous vehicle according to an embodiment of the present invention.
FIG. 2 is an internal configuration diagram of the sensor fusion unit illustrated in FIG. 1.
FIG. 3 is a diagram schematically showing an internal operation from the sensor fusion unit shown in FIG. 2 to generating a correction value.
4 is a view for explaining an operation of calculating the position and distance deviation according to the result of the marker recognition in FIG. 3.
5 is a view for explaining the operation of the automatic correction unit shown in FIG. 2.
6 is a flowchart for explaining a method for automatically calibrating an integrated sensor of an autonomous vehicle according to an embodiment of the present invention.

The present invention can be applied to various changes and can have various embodiments, and specific embodiments will be illustrated in the drawings and described in detail.

However, this is not intended to limit the present invention to specific embodiments, and should be understood to include all modifications, equivalents, and substitutes included in the spirit and scope of the present invention.

The terms used in the present application are only used to describe specific embodiments, and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly indicates otherwise. In this application, terms such as “include” or “have” are intended to indicate that a feature, number, step, operation, component, part, or combination thereof described in the specification exists, one or more other features. It should be understood that the existence or addition possibilities of fields or numbers, steps, operations, components, parts or combinations thereof are not excluded in advance.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by a person skilled in the art to which the present invention pertains. Terms such as those defined in a commonly used dictionary should be interpreted as having meanings consistent with meanings in the context of related technologies, and should not be interpreted as ideal or excessively formal meanings unless explicitly defined in the present application. Does not.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. In order to facilitate the overall understanding in describing the present invention, the same reference numerals are used for the same components in the drawings, and duplicate descriptions for the same components are omitted.

1 is a view for explaining an automatic sensor automatic correction device of an autonomous vehicle according to an embodiment of the present invention.

The automatic sensor autocorrecting device for an autonomous vehicle according to an embodiment of the present invention includes a sensor fusion unit 20 connected to the integrated sensor 10 and a display unit 30.

The integrated sensor 10 includes a camera 10a and a lidar 10b, screws for adjusting the angle of the camera 10a up and down and left and right (not shown), and screws for adjusting the angle of up and down and left and right of the camera 10a (not shown) It can be said to be a distance measuring device including, for example).

The shape of the integrated sensor 10 may vary, and the camera 10a may be installed on the upper or lower portion of the lidar 10b.

Typically, sensor fusion is a technology that enables autonomous driving by combining information recognized by each sensor into one.

The sensor fusion unit 20 in the embodiment of the present invention combines information recognized by each sensor (ie, the camera 10a, the lidar 10b) of the integrated sensor 10 into one to enable autonomous driving. In addition, it is possible to automatically correct point cloud data (ie, output data) of the lidar 10b of the integrated sensor 10.

In other words, the sensor fusion unit 20 is configured to allow the distance measurement function of the integrated sensor 10 to be normally performed even when the camera 10a and the lidar 10b are slightly displaced from each other. The point cloud data of the lidar 10b of the system is automatically corrected.

That is, the sensor fusion unit 20 compares the reference camera image and the reference lidar image of the integrated sensor 10 to calculate a deviation value for the x-axis, y-axis, and z-axis (distance), and calculates the deviation value. By generating correction values for the x-axis, y-axis, and z-axis, point cloud data of the lidar 10b is automatically corrected.

After all, the sensor fusion unit 20 modulates the point cloud data of the lidar 10b by applying the correction value to the point cloud data, which is the output data of the lidar 10b after generating the correction value. can see.

The sensor fusion unit 20 may perform automatic correction periodically or aperiodically. Here, the automatic correction performed in the sensor fusion unit 20 will be fine correction.

The large angle of the lidar 10b may be large, so that the desired fine correction may not be completed by automatic correction in the sensor fusion unit 20. Accordingly, in preparation for such a case, the sensor fusion unit 20 may output a notification message to the display unit 30 that mechanical correction is necessary when the generated correction value exceeds a preset range. When the sensor fusion unit 20 outputs a notification message, it outputs the corresponding correction value to the display unit 30 as well.

The display unit 30 may display an image including a plurality of markers (eg, a reference camera image, a reference lidar image) and a notification message that mechanical correction is required.

In addition, the display unit 30 also displays the correction value from the sensor fusion unit 20 in displaying the notification message.

Thereby, the user performs mechanical correction by operating the screw after confirming the correction value on the display unit 30. After the mechanical correction is completed, automatic correction by the sensor fusion unit 20 may be performed.

FIG. 2 is an internal configuration diagram of the sensor fusion unit 20 shown in FIG. 1, and FIG. 3 schematically shows the internal operation from the sensor fusion unit 20 shown in FIG. 2 to generating a correction value. 4 is a view for explaining the operation of calculating the position and distance deviation according to the marker recognition result in FIG. 3, and FIG. 5 is a view for explaining the operation of the automatic correction unit 29 shown in FIG. .

The sensor fusion unit 20 includes a camera image receiving unit 21, a lidar data receiving unit 22, a control unit 23, a first marker recognition unit 24, a first marker information extraction unit 25, and a second marker recognition It includes a section 26, a second marker information extraction section 27, a correction value generation section 28, and an automatic correction section 29.

The camera image receiving unit 21 receives a camera image from the camera 10a of the integrated sensor 10.

In particular, the camera image receiving unit 21 may receive a camera image that can be a reference camera image from the camera 10a of the integrated sensor 10 in the automatic correction mode. For example, the first camera image received in the automatic correction mode may be a reference camera image.

The lidar data receiving unit 22 receives point cloud data from the lidar 10b of the integrated sensor 10.

In particular, the lidar data receiving unit 22 receives point cloud data, which can be a reference lidar image, from the lidar 10b of the integrated sensor 10 in the automatic correction mode. For example, the point cloud data first received in the automatic correction mode may be a reference lidar image.

The control unit 23 controls the overall operation of the sensor fusion unit 20. That is, the control unit 23 may periodically or aperiodically generate a correction value and control an automatic correction operation based on the generated correction value.

Particularly, in the automatic correction mode, the control unit 23 places a predetermined number of markers M1, M2, and M3 in different positions and distances in the reference camera image from the camera image receiving unit 21, thereby allowing the first marker recognition unit ( 24), and a predetermined number of markers M1, M2, and M3 are placed at different positions and distances from the reference lidar image from the lidar data receiving unit 22 to the second marker recognition unit 26. send. For example, the markers M1, M2, and M3 may have a square board shape or a triangular board shape.

When the correction value generation unit 28 generates a correction value, the control unit 23 controls the automatic correction unit 29 to provide the correction value so that the correction value is the point cloud data of the lidar 10b. data).

Meanwhile, when the generated correction value exceeds a preset range, the control unit 23 may display a notification message on the display unit 30 that mechanical correction is necessary. At this time, the control unit 23 also displays the corresponding correction value on the display unit 30.

The first marker recognition unit 24 recognizes each of the markers M1, M2, and M3 in a reference camera image including a plurality of markers M1, M2, and M3 in the automatic correction mode as shown in FIG. Markers M1, M2, and M3 included in the reference camera image may be referred to as first markers.

The first marker information extraction unit 25, as shown in FIG. 3, information of each marker M1, M2, M3 recognized by the first marker recognition unit 24 (eg, position and distance information (coordinate values)) To extract. In FIG. 3, x is an x-axis coordinate, y is a y-axis coordinate, and z is a z-axis (distance) coordinate.

The second marker recognition unit 26 recognizes each of the markers M1, M2, and M3 in the reference lidar image including a plurality of markers M1, M2, and M3 in the automatic correction mode as shown in FIG. . Markers M1, M2, and M3 included in the reference lidar image may be referred to as second markers.

The second marker information extraction unit 27, as shown in FIG. 3, information of each marker M1, M2, M3 recognized by the second marker recognition unit 26 (eg, position and distance information (coordinate values)) To extract.

As shown in FIG. 3, the correction value generation unit 28 includes information of markers M1, M2, and M3 extracted from the first marker information extraction unit 25 and markers extracted by the second marker information extraction unit 27 ( M1, M2, and M3) are compared to calculate a deviation value between each other, and based on the calculated deviation value, correction values (Δx, △ y, △ z) of the x, y, z axes are generated.

Here, when calculating the deviation value, the deviation value of the position and distance between the first marker and the second marker is calculated based on the result of the marker recognition. That is, as shown in FIG. 4, the x, y, z-axis coordinate values of the vertices of each marker (ie, the first marker) in the reference camera image and the vertices of each marker (ie, the second marker) in the reference lidar image. After obtaining the coordinate values of the x, y, and z axes, respectively, by comparing the coordinate values of the respective vertices of the markers corresponding to each other between the first marker and the second marker, it is possible to calculate a deviation between the vertices corresponding to each other. The coordinate values of the x, y, and z axes of the vertices of each marker become information of the corresponding marker.

Then, based on the calculated deviation, the correction value generation unit 28 may generate correction values (Δx, Δy, Δz) of the x, y, and z axes.

In Table 1, x is the x-axis coordinate, y is the y-axis coordinate, and z is the z-axis (distance) coordinate. And, n is the number of markers.

The automatic correction unit 29 outputs the corrected data by applying the correction value generated by the correction value generation unit 28 to the point cloud data of the lidar 10b received after the correction value generation. That is, the automatic correction unit 29 automatically corrects the point cloud data by applying correction values (Δx, Δy, Δz) to the point cloud data of the lidar 10b as shown in FIG. The transmitted data is sent to the sensor data receiving device 60 at a later stage.

For example, when the automatic correction by the automatic correction unit 29 is completed, as shown in FIG. 1, the markers M1, M2, and M3 within the viewing angle range 40 of the lidar 10b and the viewing angle range of the camera 10a The markers M1, M2, and M3 in 50 will be in the same position with each other.

In the present invention described above, the camera image is not automatically corrected, but the lidar point cloud data is automatically corrected. This is because image loss occurs when the camera image is automatically corrected (modulated).

In the above-described FIG. 2, the first marker recognition unit 24 and the second marker recognition unit 26 are separated, respectively, and may be collectively referred to as a marker recognition unit in one module. In addition, although the first marker information extracting unit 25 and the second marker information extracting unit 27 are separated in FIG. 2, they may be collectively referred to as a marker information extracting unit in one module.

If necessary, the first marker recognition unit 24 and the first marker information extraction unit 25 may be integrated into one module, and the second marker recognition unit 26 and the second marker information extraction unit 27 ) Into one module.

6 is a flowchart for explaining a method for automatically calibrating an integrated sensor of an autonomous vehicle according to an embodiment of the present invention.

The sensor fusion unit 20 may set an automatic correction mode periodically or aperiodically.

Therefore, when the automatic correction mode is set, the camera image receiving unit 21 receives a camera image that can be a reference camera image from the camera 10a of the integrated sensor 10, and the lidar data receiving unit 22 receives an integrated sensor ( The point cloud data, which can be the reference lidar image, is received from the lidar 10b of 10) (S10).

Thereafter, the control unit 23 places a predetermined number of markers M1, M2, and M3 on the reference camera image from the camera image receiving unit 21 at different positions and distances, and sends them to the first marker recognition unit 24. , A predetermined number of markers M1, M2, and M3 are placed at different positions and distances in the reference lidar image from the lidar data receiving unit 22 and sent to the second marker recognition unit 26. Of course, the reference camera image and the reference lidar image in which the respective markers M1, M2, and M3 are arranged will be displayed on the display unit 30.

Subsequently, the first marker recognition unit 24 recognizes each of the markers M1, M2, and M3 in the reference camera image, and the second marker recognition unit 26 recognizes each marker M1, M2 in the reference lidar image. , M3) (S20).

Then, the first marker information extraction unit 25 extracts information (eg, position and distance information (coordinate values)) of each marker M1, M2, and M3 recognized by the first marker recognition unit 24 Then, the second marker information extraction unit 27 extracts information (eg, position and distance information (coordinate values)) of each of the markers M1, M2, and M3 recognized by the second marker recognition unit 26. (S30).

Subsequently, the correction value generation unit 28 includes information of the markers M1, M2, and M3 extracted from the first marker information extraction unit 25 and markers M1, M2 extracted by the second marker information extraction unit 27. , M3) is compared to calculate the deviation value between each other (S40).

Then, the correction value generation unit 28 generates correction values (Δx, Δy, Δz) based on the calculated deviation values, and sends them to the automatic correction unit 29 (S50).

Accordingly, the automatic correction unit 29 applies the correction values (Δx, Δy, Δz) from the correction value generation unit 28 to the point cloud data of the currently received liner 10b to automatically correct ( Modulation) is performed (S60).

Then, the automatic correction unit 29 outputs the corrected data (that is, the corrected point cloud data) to the sensor data receiving device 60 at a later stage (S70).

On the other hand, when the correction value generated in the above-described step S50 exceeds a predetermined range, the automatic message is insufficient only before the above-described step 60 is performed, so a notification message and a correction value are displayed on the display unit 30, indicating that mechanical correction is necessary. Display. Thereby, the user performs mechanical correction by operating the screw after confirming the correction value on the display unit 30. After the mechanical correction is completed, automatic correction by the sensor fusion unit 20 will be made.

In addition, the method for automatically calibrating the integrated sensor of the autonomous vehicle of the present invention described above can be implemented as a computer-readable code on a computer-readable recording medium. The computer-readable recording medium includes all types of recording devices in which data readable by a computer system is stored. Examples of computer-readable recording media include ROM, RAM, CD-ROM, magnetic tape, floppy disks, and optical data storage devices. In addition, the computer-readable recording medium can be distributed over network coupled computer systems so that the computer readable code is stored and executed in a distributed fashion. In addition, functional programs, codes, and code segments for implementing the method can be easily inferred by programmers in the technical field to which the present invention pertains.

As described above, optimal embodiments have been disclosed in the drawings and specifications. Although specific terms are used herein, they are only used for the purpose of describing the present invention and are not used to limit the scope of the present invention as defined in the claims or the claims. Therefore, those skilled in the art will appreciate that various modifications and other equivalent embodiments are possible therefrom. Therefore, the true technical protection scope of the present invention should be defined by the technical spirit of the appended claims.

10: integrated sensor 20: sensor fusion unit
21: camera image receiving unit 22: lidar data receiving unit
23: control unit 24: first marker recognition unit
25: first marker information extraction unit 26: second marker recognition unit
27: second marker information extraction unit 28: correction value generation unit
29: automatic correction unit 30: display unit

Claims (15)

The camera and the lidar are connected to an integrated sensor, and a correction value is generated based on the reference camera image of the camera and the reference lidar image of the lidar, and the output data of the lidar is automatically corrected with the correction value. The sensor fusion unit; integrated sensor automatic correction device of an autonomous vehicle, characterized in that it comprises a. The method according to claim 1,
The sensor fusion unit,
Comparing the reference camera image and the reference lidar image, calculates deviation values for the x-axis, y-axis, and z-axis, and generates correction values for the x-axis, y-axis, and z-axis with the calculated deviation values. An automatic sensor automatic correction device for autonomous vehicles. The method according to claim 2,
The sensor fusion unit,
When the generated correction value exceeds a preset range, an automatic sensor auto-correction device for an autonomous vehicle, characterized in that it outputs a notification message to a display unit that mechanical correction is necessary. The method according to claim 3,
The sensor fusion unit,
Automatic correction device for an integrated sensor of an autonomous vehicle, characterized in that it outputs a correction value exceeding the predetermined range. The method according to claim 1,
The sensor fusion unit,
A control unit for controlling the generation of the correction value and the automatic correction operation based on the generated correction value, wherein a plurality of first markers are placed on the reference camera image and a plurality of second markers are placed on the reference lidar image. ;
A marker recognition unit recognizing the first marker and the second marker;
A marker information extraction unit extracting information of the recognized first marker and information of the second marker;
A correction value generation unit comparing the information of the first marker and the information of the second marker to calculate a mutual deviation value, and generating a correction value based on the deviation value; And
And an automatic correction unit that outputs the corrected data by applying the correction value to the output data of the lidar after generating the correction value. The method according to claim 5,
The control unit,
When the generated correction value exceeds a preset range, an automatic sensor auto-correction device for an autonomous vehicle, characterized in that it outputs a notification message to a display unit that mechanical correction is necessary. The method according to claim 6,
The control unit,
Automatic correction device for an integrated sensor of an autonomous vehicle, characterized in that it outputs a correction value exceeding the predetermined range. The method according to claim 5,
The information of the first marker and the information of the second marker is an automatic correction device for an integrated sensor of an autonomous vehicle, characterized in that the x, y, z-axis coordinate values of the vertices of each marker. A method for automatically calibrating an integrated sensor in an integrated sensor automatic compensation device of an autonomous vehicle,
Generating a correction value based on the reference camera image of the camera and the reference lidar image of the lidar in the integrated sensor in which the camera and the lidar are integrated; And
Automatic correction method of the integrated sensor of the autonomous vehicle, comprising; automatically correcting the output data of the lidar with the generated correction value. The method according to claim 9,
The step of generating the correction value,
Comparing the reference camera image and the reference lidar image to calculate a deviation value for the x-axis, y-axis, z-axis; And
And generating a correction value for the x-axis, y-axis, and z-axis with the calculated deviation value. The method according to claim 10,
The step of calculating the deviation value,
Recognizing the first marker in the reference camera image in which a plurality of first markers are disposed, and recognizing the second marker in the reference lidar image in which a plurality of second markers are disposed;
Extracting information of the recognized first marker and information of the second marker; And
And comparing the extracted information of the first marker and the information of the second marker to calculate a deviation value between each other. The method according to claim 11,
The first marker and the second marker have the same number as each other,
In the extracting step, the x, y, z-axis coordinate values of the vertex of the first marker and the x, y, z-axis coordinate values of the vertex of the second marker are respectively obtained. Calibration method. The method according to claim 12,
The step of calculating the deviation value between each other,
A method for automatically calibrating an integrated sensor of an autonomous vehicle, characterized in that the coordinate values of respective vertices of the markers corresponding to each other are compared between the first marker and the second marker to calculate a deviation between the corresponding vertices. The method according to claim 9,
Between the step of generating the correction value and the step of automatically correcting,
When the generated correction value exceeds a predetermined range, displaying a notification message indicating that mechanical correction is required on the display unit; a method for automatically calibrating an integrated sensor of an autonomous vehicle, further comprising. The method according to claim 14,
The step of displaying the notification message on the display,
A method of automatically calibrating an integrated sensor of an autonomous vehicle, characterized in that a correction value exceeding the predetermined range is output together.

Images