CN113848826A

CN113848826A - Automatic vehicle offline method, device, equipment and storage medium

Info

Publication number: CN113848826A
Application number: CN202111018120.0A
Authority: CN
Inventors: 许兆基; 韩旭
Original assignee: Guangzhou Weride Technology Co Ltd
Current assignee: Guangzhou Weride Technology Co Ltd
Priority date: 2021-08-31
Filing date: 2021-08-31
Publication date: 2021-12-28
Anticipated expiration: 2041-08-31
Also published as: CN113848826B

Abstract

The invention belongs to the technical field of vehicle offline, and discloses a vehicle automatic offline method, device, equipment and storage medium. The method comprises the following steps: when the offline operation of a vehicle to be offline is required, scanning the identification information of the vehicle to be offline so as to establish communication connection with the vehicle to be offline; acquiring an offline verification item of the vehicle to be offline; verifying the vehicle to be offline through the communication connection according to the offline verification item; and when the vehicle to be off-line passes the verification, the vehicle to be off-line is identified to finish the off-line process. Through the mode, a production worker does not need professional technical knowledge, the whole process of the offline verification project can be completed only by operating according to the guidance of the application program, and the offline verification project is implemented automatically, so that the production efficiency is improved, and meanwhile, the labor cost consumption of engineers is greatly reduced.

Description

Automatic vehicle offline method, device, equipment and storage medium

Technical Field

The invention relates to the technical field of vehicle offline, in particular to a vehicle automatic offline method, device, equipment and storage medium.

Background

At present, with the popularization of automatic driving vehicles, the supply demand of the automatic driving vehicles is higher and higher, and one automatic driving vehicle is assembled in a production workshop until the automatic driving vehicle can normally run on the road, and the steps of assembling an automatic driving system, checking the working state of hardware equipment, generating and checking sensor calibration parameters, checking the state of the automatic driving system and the like are required. The existing solution needs an engineer to check, assemble and calibrate on the vehicle, needs a lot of time for the engineer to call, and cannot meet the requirement of offline of large-batch automatic driving vehicles.

The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.

Disclosure of Invention

The invention mainly aims to provide a method, a device, equipment and a storage medium for automatic vehicle offline, and aims to solve the technical problems that in the prior art, automatic driving vehicles need to consume a lot of time of engineers for calling, and cannot meet the requirement of large-batch automatic driving vehicles offline.

In order to achieve the above object, the present invention provides an automatic vehicle offline method, comprising the steps of:

when the offline operation of a vehicle to be offline is required, scanning the identification information of the vehicle to be offline so as to establish communication connection with the vehicle to be offline;

acquiring an offline verification item of the vehicle to be offline;

verifying the vehicle to be offline through the communication connection according to the offline verification item;

and when the vehicle to be off-line passes the verification, the vehicle to be off-line is identified to finish the off-line process.

Optionally, before the step of obtaining the offline verification item of the vehicle to be offline, the method further includes:

acquiring configuration information of the vehicle to be offline through the communication connection;

generating a system installation instruction and a system configuration script according to the configuration information;

and sending the system installation instruction and the system configuration script to the vehicle to be off-line so as to enable the vehicle to be off-line to install the automatic driving system according to the system installation instruction, and configuring the automatic driving system according to the system configuration script.

Optionally, the step of verifying the vehicle to be downlined through the communication connection according to the downline verification item includes:

generating a hardware verification instruction and a hardware verification script according to the offline verification item;

and sending the hardware verification instruction and the hardware verification script to the vehicle to be offline through the communication connection, so that the vehicle to be offline performs hardware detection on target hardware equipment according to the hardware verification script, and feeds back a hardware detection result.

Optionally, after the step of sending the hardware verification instruction and the hardware verification script to the vehicle to be offline through the communication connection, the method further includes:

after the hardware detection result passes, generating a system calibration instruction and a preset calibration route according to the offline verification project;

sending the system calibration instruction and the preset calibration route to the vehicle to be off-line, so that the vehicle to be off-line runs according to the preset calibration route, and recording calibration data;

after the recording of the calibration data of the vehicle to be off-line is completed, a calibration parameter generation instruction is sent so that the vehicle to be off-line determines a camera calibration image and inertial unit calibration data according to the calibration data, vehicle body attitude data is generated according to the camera calibration image, inertial unit calibration parameters are determined according to the vehicle body attitude data and the inertial unit calibration data, laser radar calibration point cloud is determined according to the calibration data, camera object coordinates are determined according to the camera calibration image, laser radar object coordinates are determined according to the laser radar calibration point cloud, laser radar calibration parameters are determined according to the camera object coordinates and the laser radar object coordinates, millimeter radar calibration data are determined according to the calibration data, millimeter radar object coordinates are determined according to the millimeter radar calibration data, and millimeter radar object coordinates are determined according to the laser radar object coordinates, And determining millimeter wave radar calibration parameters according to the laser radar calibration parameters and the millimeter wave radar object coordinates, generating calibration parameters according to the inertial unit calibration parameters, the laser radar calibration parameters and the millimeter wave radar calibration parameters, and sending the calibration parameters to a cloud.

Optionally, after the step of sending the system calibration instruction and the preset calibration route to the vehicle to be offline, the method further includes:

generating a drive test instruction according to the offline verification project;

sending the drive test instruction to the vehicle to be offline so that the vehicle to be offline runs on a preset road, collecting a drive test data packet, generating a drive test inspection flow, feeding back the drive test inspection flow, and sending the drive test data packet to the cloud end;

and generating a vehicle checking report according to the drive test checking flow, and sending the vehicle checking report to the cloud.

Optionally, the step of determining that the vehicle to be offline completes the offline process when the vehicle to be offline passes the verification includes:

sending a drive test result acquisition instruction to the cloud end, so that the cloud end determines a signal lamp image and a signal lamp vehicle identification result according to the drive test data packet, converts the signal lamp image into a signal lamp histogram, normalizes the signal lamp histogram to obtain a normalized target image, segments the normalized target image to obtain a color segmentation image, determines the geometric characteristics of the color segmentation image, determines a signal lamp area according to the geometric characteristics, obtains a signal lamp identification result according to the signal lamp area, compares the signal lamp identification result with the signal lamp vehicle identification result to obtain a signal lamp judgment result, generates a drive test result according to the signal lamp judgment result, and feeds back the drive test result;

and when the drive test result passes the verification, the vehicle to be off-line is determined to complete the off-line process.

Optionally, when the offline operation of the vehicle to be offline is required, the step of scanning the identification information of the vehicle to be offline to establish communication connection with the vehicle to be offline includes:

scanning the identification information of the vehicle to be off-line to obtain a key input page;

when receiving an authentication key, comparing the authentication key with a preset authentication key;

and after the comparison is passed, establishing communication connection with the vehicle to be offline.

In addition, in order to achieve the above object, the present invention also provides an automatic vehicle take-off device, including:

the scanning module is used for scanning the identification information of the vehicle to be offline when the vehicle to be offline is required to be offline so as to establish communication connection with the vehicle to be offline;

the acquisition module is used for acquiring an offline verification item of the vehicle to be offline;

the verification module is used for verifying the vehicle to be offline through the communication connection according to the offline verification item;

and the identification module is used for identifying the vehicle to be off-line to finish the off-line process when the vehicle to be off-line passes the verification.

In addition, to achieve the above object, the present invention also provides an automatic vehicle take-off apparatus, including: a memory, a processor, and a vehicle automatic logoff program stored on the memory and executable on the processor, the vehicle automatic logoff program configured to implement the steps of the vehicle automatic logoff method as described above.

In addition, to achieve the above object, the present invention further provides a storage medium having a vehicle automatic offline program stored thereon, which when executed by a processor implements the steps of the vehicle automatic offline method as described above.

When the offline operation of the vehicle to be offline is required, the identification information of the vehicle to be offline is scanned, so that the communication connection with the vehicle to be offline is established; acquiring an offline verification item of the vehicle to be offline; verifying the vehicle to be offline through the communication connection according to the offline verification item; and when the vehicle to be off-line passes the verification, the vehicle to be off-line is identified to finish the off-line process. Through the mode, a production worker does not need professional technical knowledge, the whole process of the offline verification project can be completed only by operating according to the guidance of the application program, and the offline verification project is implemented automatically, so that the production efficiency is improved, and meanwhile, the labor cost consumption of engineers is greatly reduced.

Drawings

FIG. 1 is a schematic flow chart diagram illustrating a first embodiment of an automatic vehicle pull-off method according to the present invention;

FIG. 2 is a schematic flow chart of a second embodiment of an automatic vehicle pull-off method according to the present invention;

FIG. 3 is a schematic flow chart of a third embodiment of an automatic vehicle pull-off method according to the present invention;

FIG. 4 is a schematic flow chart diagram illustrating a fourth embodiment of an automatic vehicle pull-off method according to the present invention;

FIG. 5 is a block diagram showing the construction of a first embodiment of the automatic vehicle take-off apparatus according to the present invention;

fig. 6 is a schematic structural diagram of an automatic vehicle offline device in a hardware operating environment according to an embodiment of the present invention.

The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.

Detailed Description

It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

An embodiment of the present invention provides an automatic vehicle offline method, and referring to fig. 1, fig. 1 is a schematic flow diagram of a first embodiment of an automatic vehicle offline method according to the present invention.

In this embodiment, the automatic vehicle offline method includes the following steps:

step S10: when the offline operation of the vehicle to be offline is required, the identification information of the vehicle to be offline is scanned so as to establish communication connection with the vehicle to be offline.

It should be noted that the execution main body of the embodiment may be a mobile terminal, for example, a smart phone, a tablet computer, and other devices running with an intelligent operating system, and an application program for vehicle offline is installed on the mobile terminal.

It should be understood that off-line means that after the vehicle is assembled, system software configuration, software and hardware function detection and the like need to be performed on the vehicle, and when the configuration, the detection and the like are qualified, the vehicle can be delivered to a user, so that the safety of the user in the driving process is ensured.

In the specific implementation, each vehicle to be offline has unique identification information, the identification information can be two-dimensional codes, bar codes and other images which can contain information, when production line workers need to perform offline operation on the vehicle to be offline, the workers open an application program and click an offline button, the application program calls a camera of a mobile terminal to scan the identification information, so that the connection information of the vehicle to be offline is obtained, and the mobile terminal establishes communication connection with the vehicle to be offline through the connection information.

It can be understood that the identification information may also be a Near Field Communication (NFC) tag, and the application program may call an NFC function of the mobile terminal and get the connection information of the vehicle to be offline by being close to the NFC tag, so as to establish a Communication connection with the vehicle to be offline. The Identification information is also a Radio Frequency Identification (RFID) tag, and the mobile terminal is connected to an RFID reader, which reads information of the RFID tag and transmits the information to the mobile terminal.

Further, in order to ensure the safety of the communication connection between the mobile terminal and the vehicle to be offline, step S10 includes: scanning the identification information of the vehicle to be off-line to obtain a key input page; when receiving an authentication key, comparing the authentication key with a preset authentication key; and after the comparison is passed, establishing communication connection with the vehicle to be offline.

In the specific implementation, the mobile terminal and the vehicle to be offline can be in communication connection with the cloud in advance, the vehicle to be offline and the cloud can be in communication connection through a preset authentication key, the mobile terminal sends the connection information of the vehicle to be offline to the mobile terminal after scanning identification information, the connection information comprises the preset authentication key, an application program interface can display a key input page, a worker inputs the authentication key, the mobile terminal compares the authentication key with the preset authentication key, after the comparison is passed, the comparison success information is sent to the cloud, and communication connection between the mobile terminal and the vehicle to be offline is established through the cloud.

It can be understood that, after the authentication key passes the comparison with the preset authentication key, the mobile terminal can also directly establish communication connection with the vehicle to be offline without passing through the cloud, thereby avoiding losing communication connection with the cloud when the wireless signal is poor, causing the vehicle to be offline to lose connection, and affecting the offline process of the vehicle to be offline.

It should be noted that, by scanning the identification information of the vehicle to be offline, a key input page is obtained; when receiving an authentication key, comparing the authentication key with a preset authentication key; after the comparison is passed, the communication connection is established with the vehicle to be off-line, and the data security of the whole process can be ensured when the vehicle to be off-line is verified.

Step S20: and acquiring an offline verification item of the vehicle to be offline.

In specific implementation, the offline verification project can completely detect and verify whether software and hardware of the vehicle to be offline can normally operate, and the offline verification project comprises hardware data automatic detection, positioning and sensor calibration parameter generation, calibration parameter verification, automatic driving system automatic verification and other projects.

It can be understood that after the mobile terminal establishes communication connection with the vehicle to be offline, the offline verification item required by the vehicle to be offline is acquired from the cloud; or the mobile terminal stores the offline verification item, the mobile terminal sends the version number of the offline verification item to the cloud, the cloud judges whether the version number is the latest offline verification item after receiving the version number, and if the version number is not the latest version, the latest version of the offline verification item is sent to the mobile terminal.

In a specific implementation, due to different configurations and functions of different vehicles to be offline, items to be verified may not be completely the same. For example: the radar set on the vehicle A to be off-line is a laser radar, and the radar set on the vehicle B to be off-line is a millimeter wave radar, so that the methods used by the two vehicle detection and verification radars may be different. The above are merely examples, and the present embodiment is not limited thereto.

Step S30: and verifying the vehicle to be offline through the communication connection according to the offline verification item.

The offline verification items include a sequence of real-time verification items, workers operate through the sequence of steps in the application program, after receiving operation instructions of the workers, the mobile terminal generates corresponding offline verification item instructions and sends the offline verification item instructions to the vehicle to be offline through communication connection, and the vehicle to be offline executes corresponding verification operations according to the offline verification item instructions, so that various verifications in the offline verification items are automatically completed.

It can be understood that, because each verification step in the offline verification project is executed in sequence, rather than synchronously, when some verification project does not pass, the application program can prompt a worker that a certain software or hardware has a problem, and lists various solutions, the worker can overhaul according to the solutions, test and verify the project again after the overhaul is finished, if the verification does not pass, the worker can remotely ask for help from an engineer through the application program, the engineer can remotely check various detection data, and debug and repair the offline vehicle, thereby ensuring the production continuity of the production line.

Step S40: and when the vehicle to be off-line passes the verification, the vehicle to be off-line is identified to finish the off-line process.

It should be understood that, when the vehicle to be offline is completed and passes all offline verification items, it indicates that there is no problem in software, hardware, system, etc. of the vehicle to be offline, and the user can use the vehicle directly, and at this time, the offline vehicle is determined to have completed the offline process, and can be delivered to the user.

In the embodiment, when the offline operation of the vehicle to be offline is required, the identification information of the vehicle to be offline is scanned so as to establish communication connection with the vehicle to be offline; acquiring an offline verification item of the vehicle to be offline; verifying the vehicle to be offline through the communication connection according to the offline verification item; and when the vehicle to be off-line passes the verification, the vehicle to be off-line is identified to finish the off-line process. Through the mode, a production worker does not need professional technical knowledge, the whole process of the offline verification project can be completed only by operating according to the guidance of the application program, and the offline verification project is implemented automatically, so that the production efficiency is improved, and meanwhile, the labor cost consumption of engineers is greatly reduced.

Referring to fig. 2, fig. 2 is a schematic flow chart of a second embodiment of an automatic vehicle offline method according to the present invention.

Based on the first embodiment, before the step S20, the method for automatically getting off-line of the vehicle according to the embodiment further includes:

step S11: and acquiring the configuration information of the vehicle to be offline through the communication connection.

It should be noted that, after the mobile terminal establishes a communication connection with the vehicle to be offline, the current configuration information of the vehicle can be obtained from the vehicle to be offline, and the configuration information includes hardware configuration, software configuration, system configuration, and the like.

It can be understood that, generally, when the vehicle to be offline is connected with the mobile terminal for the first time, only the basic operating system is installed on the vehicle to be offline, and basic data, service data and the like of the system are not completely configured.

Step S12: and generating a system installation instruction and a system configuration script according to the configuration information.

The automatic driving system is integrated and packaged in advance, and includes a high-definition map, basic data, service data, and the like. On the production line, a worker only needs to insert the system disk into a host of a vehicle to be offline, and the vehicle to be offline can automatically recognize data in the system disk. The system disk can be a nonvolatile storage medium such as a U disk.

In a specific implementation, a worker clicks on an application program to start installation, the mobile terminal generates a system installation instruction, and generates a system configuration script according to configuration information of a vehicle to be offline.

Step S13: and sending the system installation instruction and the system configuration script to the vehicle to be off-line so as to enable the vehicle to be off-line to install the automatic driving system according to the system installation instruction, and configuring the automatic driving system according to the system configuration script.

It should be noted that after the offline vehicle receives the system installation instruction, the automatic driving system is installed according to the data in the system disk, and the high-definition map data, the basic data, the service data, and the like are decompressed. When the automatic driving system is installed, the automatic driving system is usually undifferentiated, and the system configuration script automatically configures the automatic driving system, so that the automatic driving system is completely matched with the configuration of the vehicle to be off-line.

The embodiment acquires the configuration information of the vehicle to be offline through the communication connection; generating a system installation instruction and a system configuration script according to the configuration information; and sending the system installation instruction and the system configuration script to the vehicle to be off-line so as to enable the vehicle to be off-line to install the automatic driving system according to the system installation instruction, and configuring the automatic driving system according to the system configuration script. By the mode, the application program acquires the configuration information of the vehicle after the vehicle to be off-line is connected, and configures the automatic driving system according to the configuration information of the vehicle after the automatic driving system is automatically installed on the vehicle, so that the effect that the vehicle to be off-line corresponds to the automatic driving system one to one is achieved.

Referring to fig. 3, fig. 3 is a schematic flow chart of a third embodiment of an automatic vehicle offline method according to the present invention.

Based on the first embodiment, the method for automatically getting off line of the vehicle in the embodiment at the step S30 includes:

step S31: and generating a hardware verification instruction and a hardware verification script according to the offline verification item.

In a specific implementation, the offline verification item comprises hardware detection, when the hardware detection step is reached according to the step sequence in the offline verification item, a worker clicks the hardware detection, and the mobile terminal generates a hardware verification instruction and a hardware verification script.

It should be noted that the hardware verification script may be a general verification script, or a hardware verification script generated according to the hardware configuration of the vehicle to be offline.

Step S32: and sending the hardware verification instruction and the hardware verification script to the vehicle to be offline through the communication connection, so that the vehicle to be offline performs hardware detection on target hardware equipment according to the hardware verification script, and feeds back a hardware detection result.

It can be understood that, after the vehicle to be offline receives the hardware verification instruction and the hardware verification script, the hardware verification script is executed according to the hardware verification instruction, the hardware verification script comprehensively detects hardware devices on the vehicle, and the hardware detection items include: the hardware detection method comprises the following steps of hard disk working state, disk configuration, system starting time, video card configuration and pressure test performance, CPU configuration and pressure test performance, memory size, millimeter wave radar signals, line control signals, GPS signals, network signals, laser radar network card speed, whether line sequence connection of a camera is correct, camera frame loss conditions and the like. The target hardware device includes: hard disk, magnetic disk, display card, CPU, memory, millimeter wave radar, wire control, GPS chip, network card, laser radar network card and camera.

It should be noted that, because hardware generally works in a combined manner and data interaction is performed between the hardware, connectivity between the hardware needs to be tested during hardware detection, and data generated during hardware detection can be analyzed to determine whether the hardware can work normally. For example: when the GPS positioning module is detected, the connectivity of other hosts is detected, positioning data collected by the GPS positioning module is analyzed, and whether the positioning data is abnormal or not is judged.

It should be noted that, the hardware on the offline vehicle supports software control at the same time, so a hardware interface for software control needs to be detected, and whether the hardware can be controlled to realize a corresponding function is determined by calling an interface corresponding to the hardware, so as to determine whether the hardware can normally work. For example: and calling a reversing image function of the high-definition reversing camera, and judging whether the reversing camera can normally work or not according to the display image.

In the specific implementation, each time one of the hardware detection is finished, the hardware detection result is fed back to the mobile terminal in real time, the mobile terminal displays the hardware detection result in real time, after the hardware detection project is finished, hardware which fails to operate or cannot operate to reach the standard is prompted to workers, repair suggestions are provided for repairing, if the workers cannot repair the hardware, help can be sought through an application program, an engineer remotely supports the repair, and after the repair is finished, the hardware detection is carried out again until all target hardware devices operate to reach the standard.

Further, after all target hardware devices pass the verification, after the step of sending the hardware verification instruction and the hardware verification script to the vehicle to be offline through the communication connection, the method further includes: after the hardware detection result passes, generating a system calibration instruction and a preset calibration route according to the offline verification project; sending the system calibration instruction and the preset calibration route to the vehicle to be off-line, so that the vehicle to be off-line runs according to the preset calibration route, and recording calibration data; after the recording of the calibration data of the vehicle to be off-line is completed, a calibration parameter generation instruction is sent so that the vehicle to be off-line determines a camera calibration image and inertial unit calibration data according to the calibration data, vehicle body attitude data is generated according to the camera calibration image, inertial unit calibration parameters are determined according to the vehicle body attitude data and the inertial unit calibration data, laser radar calibration point cloud is determined according to the calibration data, camera object coordinates are determined according to the camera calibration image, laser radar object coordinates are determined according to the laser radar calibration point cloud, laser radar calibration parameters are determined according to the camera object coordinates and the laser radar object coordinates, millimeter radar calibration data are determined according to the calibration data, millimeter radar object coordinates are determined according to the millimeter radar calibration data, and millimeter radar object coordinates are determined according to the laser radar object coordinates, And determining millimeter wave radar calibration parameters according to the laser radar calibration parameters and the millimeter wave radar object coordinates, generating calibration parameters according to the inertial unit calibration parameters, the laser radar calibration parameters and the millimeter wave radar calibration parameters, and sending the calibration parameters to a cloud.

It should be noted that after determining that all target hardware devices pass the verification according to the hardware detection result, the application program jumps to a next offline verification item page, before performing a next offline verification item, the application program prompts a worker to transport a vehicle to be offline to a calibration site, after the vehicle to be offline is transported to the calibration site, the worker may click to start calibration in the application program, and the application program generates a system calibration instruction and a preset calibration route and sends the system calibration instruction and the preset calibration route to the vehicle to be offline.

It can be understood that after the vehicle to be off-line receives the system calibration instruction, the vehicle to be off-line automatically runs in the calibration field according to the preset calibration route, and automatically collects and records the calibration object in the field, so as to generate calibration data, and the vehicle to be off-line automatically calculates the calibration parameters according to the calibration data, writes the calibration parameters into a local configuration file, and uploads the calibration parameters to the cloud for storage. The preset calibration route can be a cross route in the calibration site.

Further, before a vehicle to be offline initializes sensor calibration parameters, brake calibration parameters to be offline are required, in a closed field, an application program sends a preset code to the vehicle to be offline, the vehicle to be offline generates a calibration track in the closed field according to the preset code, a worker starts the vehicle to be offline automatically, a control module of the vehicle to be offline drives the vehicle to be offline along the track by sending a brake accelerator instruction and a steering wheel instruction, a data acquisition module automatically acquires positioning and speed difference during driving to calculate a brake meter and an accelerator meter of the vehicle, and acquired point cloud data is used for positioning calibration and sensor calibration.

It can be understood that the brake meter comprises the corresponding relation between the opening degree of the brake pedal and the acceleration, and the accelerator meter comprises the corresponding relation between the opening degree of the accelerator pedal and the acceleration, so that the speed of the vehicle can be controlled more accurately through the brake meter and the accelerator meter during automatic driving.

When the point cloud data is used for positioning and calibrating, the point cloud data acquired by the vehicle to be off-line is compared with the global point cloud data in the closed field, so that the specific position of the vehicle to be off-line in the closed field can be determined, and then the vehicle to be off-line is positioned and calibrated according to the positioning data acquired by the positioning module of the vehicle to be off-line.

In specific implementation, the system calibration comprises inertial unit calibration, laser radar calibration and millimeter wave radar calibration. Sensor calibration is a basic requirement of automatic driving, and when a plurality of sensors (such as a camera, a laser radar, a millimeter wave radar and the like) are mounted on a vehicle, the coordinate relationship between the sensors needs to be determined.

It should be noted that the inertial unit is a device for measuring the three-axis attitude angle (or angular rate) and acceleration of an object, and when calibrating the inertial unit, because the attitude change between the inertial unit and the lidar or the camera satisfies a certain constraint relationship, the coordinate conversion relationship between the inertial unit and the lidar or the camera, that is, the calibration parameter of the inertial unit, is determined according to the data collected by the inertial unit and the calibration data collected by the lidar or the camera. When the laser radar is calibrated, the calibration data collected by the laser radar and the camera are calculated, so that the coordinate conversion relation between the laser radar and the camera is determined, the calibration parameters of the laser radar are obtained, the calibration parameters of the millimeter wave radar can be obtained in the same way, and the coordinate relation between the sensors on the vehicle to be off-line is determined.

In a specific implementation, an inertial unit, a laser radar and a millimeter wave radar are calibrated by taking a camera calibration image captured by a camera (camera) in a calibration field as a reference. In order to facilitate the calibration of the vehicle to be off-line, a calibration object with an obvious shape is arranged in a calibration field, when the vehicle to be off-line passes through the calibration object, calibration data can be recorded in real time by each sensor on the vehicle body, after the recording of the calibration data is completed, the fact that the recording of the calibration data is completed can be displayed on an application program, the calibration parameter calculation can be carried out, after a worker clicks a calibration parameter calculation button, a mobile terminal sends a calibration parameter generation instruction to the vehicle to be off-line, and then the vehicle to be off-line starts to calculate the calibration parameters of each sensor.

It can be understood that the camera calibration image and the inertial unit calibration data are calibration data recorded by the camera and the inertial unit with the same time line as a reference, the camera calibration image comprises image information of a calibration plate recorded by the camera, when the posture of the vehicle body of the vehicle to be off-line changes, the calibration plate also generates corresponding posture angle change in the camera calibration image, the posture angle change detected by the inertial unit is determined according to the data at the same moment of the inertial unit calibration data, and the posture angle change captured by the camera is compared with the posture angle change detected by the inertial unit, so that a conversion parameter between the camera calibration image and the inertial unit calibration parameter can be determined, namely the inertial unit calibration parameter.

Similarly, when the laser radar is calibrated, a camera calibration image of a calibration object captured by a camera and a laser radar calibration point cloud of the calibration object collected by the laser radar are determined at the same time, a coordinate system is established in the camera calibration image, the coordinate of the calibration object in the coordinate system, namely the coordinate of the camera object, is determined, the coordinate system is established in the laser radar calibration point cloud, the coordinate of the calibration object in the coordinate system, namely the coordinate of the laser radar object is determined, and the conversion relation between the camera object coordinate and the laser radar object coordinate is calculated, so that the laser radar calibration parameters are obtained.

In the specific implementation, when the millimeter wave radar is calibrated, the millimeter wave radar calibration data of a calibration object acquired by the millimeter wave radar at the same moment and the laser radar calibration point cloud of the calibration object acquired by the laser radar are also determined by means of the laser radar, the coordinate of the calibration object in the millimeter wave radar calibration data, namely the millimeter wave radar object coordinate, and the coordinate of the calibration object in the laser radar calibration point cloud, namely the laser radar object coordinate are calculated, finally, the conversion relation between the millimeter wave radar object coordinate and the laser radar object coordinate is calculated, and the conversion relation parameter between the millimeter wave radar and the camera, namely the millimeter wave radar calibration parameter, is obtained based on the laser radar calibration parameter.

Further, when a long-focus camera and a short-focus camera are simultaneously arranged on a vehicle with an offline, the two cameras need to be calibrated, a long-focus calibration image and a short-focus calibration image are determined at the same moment, a long-focus target image in a preset range in the long-focus calibration image is obtained, and because the image captured by the cameras generates distortion at the edge and the near position, a preset range with small image distortion needs to be selected, for example, a calibration object in an area of 50 meters away from the image is selected. Simultaneously acquiring a short-focus target image in the short-focus calibration image within the preset range, converting the coordinates of calibration objects in the long-focus target image and the short-focus target image, calculating conversion parameters, and acquiring camera calibration parameters,

it should be noted that, after the calibration parameters are generated and stored, the vehicle to be offline sends a calibration completion signal to the mobile terminal, and the application program prompts the worker that the system calibration process is completed, so that the offline verification project of the next step can be developed.

Further, in order to more comprehensively verify the vehicle to be off-line, after the step of sending the system calibration instruction and the preset calibration route to the vehicle to be off-line, the method further includes: generating a drive test instruction according to the offline verification project; sending the drive test instruction to the vehicle to be offline so that the vehicle to be offline runs on a preset road, collecting a drive test data packet, generating a drive test inspection flow, feeding back the drive test inspection flow, and sending the drive test data packet to the cloud end; and generating a vehicle checking report according to the drive test checking flow, and sending the vehicle checking report to the cloud.

It should be understood that after the verification project of system calibration is completed, the drive test verification needs to be performed, so as to detect the running condition of the vehicle to be offline in the real environment. At this time, the application program prompts the worker to transport the vehicle to be taken off to a drive test site, and the drive test site comprises information in the actual road, such as traffic lights, zebra crossings and the like.

It can be understood that a worker clicks a drive test start button on an application program, the application program generates a drive test instruction and sends the drive test instruction to a vehicle to be off-line, the vehicle to be off-line automatically runs on a drive test site after receiving the drive test instruction, an automatic driving system on the vehicle to be off-line automatically drives according to road information in the drive test site, the application program displays a complete inspection flow for the worker to check in the drive test process, and the inspection flow comprises vehicle traffic light inspection, brake inspection, accelerator inspection, steering wheel inspection and collision inspection. And after the checking is finished, a vehicle checking report is generated and uploaded to a cloud record.

It should be understood that, the vehicle waiting to be off-line can automatically collect the road data of the fixed road in the process of the drive test, the road data is collected by the laser radar, the millimeter wave radar and the camera on the vehicle waiting to be off-line, and the road data is sent to the cloud end, and the cloud end can analyze whether the laser radar, the millimeter wave radar and the camera normally operate or not according to the road data, and whether the object detected and the response made in the given road section are correct or not. And a drive test result is obtained.

According to the embodiment, a hardware verification instruction and a hardware verification script are generated according to the offline verification item; and sending the hardware verification instruction and the hardware verification script to the vehicle to be offline through the communication connection, so that the vehicle to be offline performs hardware detection on target hardware equipment according to the hardware verification script, and feeds back a hardware detection result. By the mode, full-automatic offline verification items such as hardware verification, system calibration, drive test verification and the like are performed on the vehicles to be offline, and strict software and hardware detection processes are performed, so that the vehicles to be offline can be comprehensively detected and verified, and the delivery quality of batch offline automatic driving vehicles is guaranteed.

Referring to fig. 4, fig. 4 is a schematic flow chart illustrating a fourth embodiment of an automatic vehicle offline method according to the present invention.

Based on the third embodiment, the method for automatically getting off line of the vehicle in the embodiment at the step S40 includes:

step S41: sending a road test result acquisition instruction to the cloud end, so that the cloud end determines a signal lamp image and a signal lamp vehicle identification result according to the road test data packet, converts the signal lamp image into a signal lamp histogram, normalizes the signal lamp histogram to obtain a normalized target image, segments the normalized target image to obtain a color segmentation image, determines the geometric characteristics of the color segmentation image, determines a signal lamp area according to the geometric characteristics, obtains a signal lamp identification result according to the signal lamp area, compares the signal lamp identification result with the signal lamp vehicle identification result to obtain a signal lamp judgment result, generates a road test result according to the signal lamp judgment result, and feeds back the road test result.

It should be noted that, after the road test is finished, the worker clicks a button for obtaining the road test result on the application program, the application program generates a road test result obtaining instruction and sends the road test result obtaining instruction to the cloud, and the cloud sends the corresponding road test result to the mobile terminal.

In concrete implementation, the cloud analyzes the drive test data packet after receiving the drive test data packet, and the drive test data packet contains all data of the vehicle to be offline in the drive test process, including data collected by the sensor, data judged by the vehicle according to the data collected by the sensor, and the like.

It can be understood that, the unavoidable one of driving process during the signal lamp, consequently the vehicle of waiting to roll off the production line is crucial to the rate of accuracy that the discernment of signal lamp detected, and the high in the clouds obtains waiting to roll off the production line image that the camera was gathered when passing through the signal lamp according to the drive test data packet, signal lamp image promptly, and the high in the clouds need carry out the histogram equalization with the signal lamp image at first and obtain the signal lamp histogram, promptly: histogram equalization is performed on each channel (R, G, B) data of the signal lamp images, and then the signal lamp images are combined into a 3-channel image. Since the correlation between R, G, B components in the RGB color space is high, the influence by illumination is large, which is not favorable for color division. Therefore, 3 channel data of RGB are normalized to obtain a normalized target image, and the normalization formula is:

wherein R is the normalized value of the R channel, G is the normalized value of the G channel, and B is the normalized value of the B channel.

Note that since the value of R, G, B of the traffic light differs in the traffic light images in different lighting environments, the threshold range of the value of the traffic light R, G, B is determined from the traffic light images in the respective lighting environments. According to the threshold range, the area of the normalized target image can be determined, namely, the color segmentation image can be obtained, and due to the fact that other interference factors exist in the environment and the color segmentation image is not necessarily the area of the signal and the like, the signal lamp area in the color segmentation image needs to be determined according to the geometric characteristics of the signal lamp, basic geometric characteristics of the area, such as length, width, length-width ratio and the like, are extracted, the area close to a circle is used as the signal lamp area, the signal lamp is identified according to the color of the signal lamp area, a signal lamp identification result is obtained, the signal lamp identification result is compared with the signal lamp vehicle identification result of the signal lamp of the vehicle to be offline, a signal lamp judgment result is obtained, and when the correspondence is achieved, the success of identifying the signal lamp of the vehicle to be offline is indicated.

In a similar way, the cloud terminal also simulates automatic driving based on data collected by the sensor of the vehicle to be off-line, so that simulated steering wheel, brake and throttle control instructions are generated and compared with actual control instructions of the vehicle to be off-line, an automatic driving decision result is obtained, and whether the decision of the vehicle to be off-line is correct or not is judged according to the automatic driving decision result.

In specific implementation, a drive test result can be obtained according to a signal lamp judgment result and an automatic driving decision result.

Step S42: and when the drive test result passes the verification, the vehicle to be off-line is determined to complete the off-line process.

It should be noted that when the identification of the signal lamps of the vehicles waiting to be offline is correct and is consistent with the decision made by the cloud according to the sensor data, it indicates that the drive test result is passed.

In a specific implementation, all offline verification items are developed according to a certain sequence, and the next verification item is opened only after the offline verification items pass, so that when a drive test result passes verification, all offline verification items of the vehicle to be offline pass verification, and the vehicle can be delivered to a user.

In this embodiment, a drive test result obtaining instruction is sent to the cloud, so that the cloud determines a signal lamp image and a signal lamp vehicle identification result according to the drive test data packet, converts the signal lamp image into a signal lamp histogram, normalizes the signal lamp histogram to obtain a normalized target image, segments the normalized target image to obtain a color segmentation image, determines geometric features of the color segmentation image, determines a signal lamp region according to the geometric features, obtains a signal lamp identification result according to the signal lamp region, compares the signal lamp identification result with the signal lamp vehicle identification result to obtain a signal lamp judgment result, generates a drive test result according to the signal lamp judgment result, and feeds back the drive test result; and when the drive test result passes the verification, the vehicle to be off-line is determined to complete the off-line process. Through the mode, the cloud end verifies and analyzes the key drive test data, so that the running condition of the vehicle in a real scene can be accurately judged, the whole offline process is completed after the drive test data are verified, and the vehicle can be directly delivered.

In addition, an embodiment of the present invention further provides a storage medium, where the storage medium stores a vehicle automatic offline program, and the vehicle automatic offline program, when executed by a processor, implements the steps of the vehicle automatic offline method as described above.

Since the storage medium adopts all technical solutions of all the embodiments, at least all the beneficial effects brought by the technical solutions of the embodiments are achieved, and no further description is given here.

Referring to fig. 5, fig. 5 is a block diagram illustrating a first embodiment of an automatic vehicle take-off apparatus according to the present invention.

As shown in fig. 5, the automatic vehicle offline device according to the embodiment of the present invention includes:

the scanning module is used for scanning the identification information of the vehicle to be offline when the vehicle to be offline is required to be offline, so as to establish communication connection with the vehicle to be offline.

The obtaining module 10 is configured to obtain an offline verification item of the vehicle to be offline.

And the verification module 20 is used for verifying the vehicle to be offline through the communication connection according to the offline verification item.

And the identifying module 30 is used for identifying the vehicle to be off-line to finish the off-line process when the vehicle to be off-line passes the verification.

It should be understood that the above is only an example, and the technical solution of the present invention is not limited in any way, and in a specific application, a person skilled in the art may set the technical solution as needed, and the present invention is not limited thereto.

In this embodiment, when a vehicle to be offline needs to be offline, the scanning module 10 scans identification information of the vehicle to be offline to establish communication connection with the vehicle to be offline; the obtaining module 20 obtains an offline verification item of the vehicle to be offline; the verification module 30 verifies the vehicle to be offline through the communication connection according to the offline verification item; and the affirming module 40 affirms the vehicle to be off-line to finish the off-line process when the vehicle to be off-line passes the verification. Through the mode, a production worker does not need professional technical knowledge, the whole process of the offline verification project can be completed only by operating according to the guidance of the application program, and the offline verification project is implemented automatically, so that the production efficiency is improved, and meanwhile, the labor cost consumption of engineers is greatly reduced.

It should be noted that the above-described work flows are only exemplary, and do not limit the scope of the present invention, and in practical applications, a person skilled in the art may select some or all of them to achieve the purpose of the solution of the embodiment according to actual needs, and the present invention is not limited herein.

In addition, the technical details that are not elaborated in the present embodiment can be referred to the automatic vehicle offline method provided by any embodiment of the present invention, and are not described herein again.

Referring to fig. 6, fig. 6 is a schematic structural diagram of an automatic vehicle offline device in a hardware operating environment according to an embodiment of the present invention.

As shown in fig. 6, the vehicle automatic pull-down apparatus may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a Wireless interface (e.g., a Wireless-Fidelity (Wi-Fi) interface). The Memory 1005 may be a Random Access Memory (RAM) Memory, or may be a Non-Volatile Memory (NVM), such as a disk Memory. The memory 1005 may alternatively be a storage device separate from the processor 1001.

Those skilled in the art will appreciate that the configuration shown in fig. 6 does not constitute a limitation of the automatic vehicle downline apparatus and may include more or fewer components than those shown, or some components in combination, or a different arrangement of components.

As shown in fig. 6, a memory 1005, which is a storage medium, may include therein an operating system, a network communication module, a user interface module, and a vehicle automatic offline program.

In the automatic vehicle offline apparatus shown in fig. 6, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 of the vehicle automatic offline device of the present invention may be provided in the vehicle automatic offline device, which calls the vehicle automatic offline program stored in the memory 1005 through the processor 1001 and performs the following operations:

acquiring an offline verification item of the vehicle to be offline;

Further, the processor 1001 may call the vehicle automatic offline program stored in the memory 1005, and also perform the following operations:

Further, it is to be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.

The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.

Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention or portions thereof that contribute to the prior art may be embodied in the form of a software product, where the computer software product is stored in a storage medium (e.g. Read Only Memory (ROM)/RAM, magnetic disk, optical disk), and includes several instructions for enabling a terminal device (e.g. a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.

The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.

Claims

1. An automatic vehicle offline method, characterized in that the automatic vehicle offline method comprises:

acquiring an offline verification item of the vehicle to be offline;

2. The method of claim 1, wherein the step of obtaining the offline validation item of the offline vehicle is preceded by the step of:

3. The method of claim 1, wherein the step of validating the vehicle to be downlinked over the communication connection in accordance with the downline validation item comprises:

4. The method of claim 3, wherein after the step of sending the hardware validation instruction and the hardware validation script to the vehicle to be downlinked over the communication connection, further comprising:

5. The method of claim 4, wherein the step of sending the system calibration instructions and the preset calibration route to the vehicle to be offline further comprises, after the step of sending the system calibration instructions and the preset calibration route to the vehicle to be offline:

6. The method of claim 5, wherein the step of identifying that the vehicle to be downlinked completes the downline procedure upon verification of the vehicle to be downlinked comprises:

7. The method according to any one of claims 1 to 6, wherein the step of scanning the identification information of the vehicle to be offline for establishing a communication connection with the vehicle to be offline when the vehicle to be offline is required to be offline comprises:

8. An automatic vehicle take-off device, comprising:

9. An automatic vehicle take-off device, comprising: a memory, a processor, and a vehicle automatic logoff program stored on the memory and executable on the processor, the vehicle automatic logoff program configured to implement the vehicle automatic logoff method of any of claims 1 to 7.

10. A storage medium having stored thereon a vehicle automatic logoff program which, when executed by a processor, implements the vehicle automatic logoff method according to any one of claims 1 to 7.