WO2021093420A1

WO2021093420A1 - Vehicle navigation method and apparatus, and computer readable storage medium

Info

Publication number: WO2021093420A1
Application number: PCT/CN2020/112216
Authority: WO
Inventors: 赵健章; 刘瑞超
Original assignee: 深圳创维数字技术有限公司
Priority date: 2019-11-12
Filing date: 2020-08-28
Publication date: 2021-05-20
Also published as: CN110837814A; CN110837814B

Abstract

Disclosed in the present application is a vehicle navigation method. The vehicle navigation method comprises the following steps: when determining, on the basis of the current first position information of a vehicle, that the vehicle is located at a first specified position corresponding to a target storage location, obtaining a coordinate origin corresponding to the vehicle; controlling, on the basis of the coordinate origin, the vehicle to rotate, and on the basis of a first ground image currently photographed by a photographing apparatus installed on the vehicle, determining whether an edge marking line corresponding to the target storage location is perpendicular to the vehicle; and when the edge marking line is perpendicular to the vehicle, controlling the vehicle to stop rotating.

Description

Vehicle navigation method, device and computer readable storage medium

This application requires Shenzhen Skyworth Digital Technology Co., Ltd. to submit the priority of a Chinese patent application with the application number 201911117651.8 and the invention title of "Vehicle Navigation Method, Device and Computer Readable Storage Medium" to the Chinese Patent Office on November 12, 2019. The entire content is incorporated into the application by reference.

Technical field

This application relates to the field of intelligent driving technology, and in particular to a vehicle navigation method, device, and computer-readable storage medium.

Background technique

SLAM (simultaneous Localization and mapping, real-time positioning and map construction) includes two major functions: positioning and mapping. Among them, the main function of mapping is to understand the surrounding environment and establish the corresponding relationship between the surrounding environment and space; the main function of positioning is to judge the position of the car body on the map based on the built map, so as to obtain the information in the environment. Secondly, lidar is an active detection sensor that does not depend on external light conditions and has high-precision ranging information. Therefore, the SLAM method based on lidar is still the most widely used method in the robot SLAM method, and in ROS (Robot Operating System, robot software platform) SLAM applications have also been very extensive.

In practical applications, in order to save storage space, the distance between pallet positions should be reduced as much as possible. Usually, the aisle between the two deep pile positions is only a little longer than the length of the vehicle. The existing navigation method is difficult. This allows the vehicle to enter the target location accurately and quickly, which in turn affects the navigation efficiency of the vehicle.

The above content is only used to assist the understanding of the technical solutions of this application, and does not mean that the above content is recognized as prior art.

Technical solutions

The main purpose of this application is to provide a vehicle navigation method, device, and computer-readable storage medium, aiming to solve the technical problem that the existing navigation method is difficult to make the vehicle enter the target location accurately and quickly.

To achieve the above objective, the present application provides a vehicle navigation method, which includes the following steps:

When it is determined that the vehicle is located at the first designated location corresponding to the target storage location based on the current first location information of the vehicle, acquiring the coordinate origin corresponding to the vehicle;

Controlling the rotation of the vehicle based on the origin of the coordinates, and determining whether the edge identification line corresponding to the target storage location is perpendicular to the vehicle based on the first ground image currently captured by the camera installed on the vehicle;

When the edge marking line is perpendicular to the vehicle, the vehicle is controlled to stop rotating.

In addition, in order to achieve the above object, the present application also provides a vehicle navigation device, the vehicle navigation device comprising: a memory, a processor, and computer-readable instructions stored in the memory and running on the processor, When the computer-readable instructions are executed by the processor, the steps of the vehicle navigation method described in any one of the above are implemented.

In addition, in order to achieve the above object, the present application also provides a computer-readable storage medium having computer-readable instructions stored on the computer-readable storage medium, and when the computer-readable instructions are executed by a processor, any one of the above is realized. The steps of the vehicle navigation method described in the item.

This application obtains the coordinate origin corresponding to the vehicle when it is determined that the vehicle is located at the first designated position corresponding to the target storage location based on the current first position information of the vehicle; then controls the rotation of the vehicle based on the coordinate origin, and Based on the first ground image currently captured by the camera device installed on the vehicle, it is determined whether the edge identification line corresponding to the target location is perpendicular to the vehicle; and then when the edge identification line is perpendicular to the vehicle, the control station is controlled When the vehicle stops rotating and moves in the narrow lane corresponding to the vehicle location, by rotating the vehicle to make the vehicle perpendicular to the edge marking line of the target location, so that the vehicle and the target location can be accurately aligned, so that the vehicle can enter accurately and quickly Target storage location to improve the efficiency of vehicle navigation.

Description of the drawings

FIG. 1 is a schematic structural diagram of a path navigation device in a hardware operating environment involved in a solution of an embodiment of the application;

FIG. 2 is a schematic flowchart of a first embodiment of a vehicle navigation method according to this application;

Fig. 3 is a detailed flow of the step of determining whether the edge marking line of the target location corresponding to the first designated location is perpendicular to the vehicle based on the first ground image currently captured by the camera device installed on the vehicle in the vehicle navigation method of this application Schematic diagram

4 is a schematic diagram of a scene in an embodiment of the route navigation method of this application;

Fig. 5 is a schematic flowchart of a second embodiment of a vehicle navigation method according to this application.

The realization, functional characteristics, and advantages of the purpose of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings.

Embodiments of the present invention

It should be understood that the specific embodiments described here are only used to explain the application, and not used to limit the application.

As shown in FIG. 1, FIG. 1 is a schematic structural diagram of a path navigation device in a hardware operating environment involved in a solution of an embodiment of the present application.

As shown in FIG. 1, the route navigation apparatus may include a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, and a communication bus 1002. Among them, the communication bus 1002 is used to implement connection and communication between these components. The user interface 1003 may include a display screen (Display) and an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface). The memory 1005 may be a high-speed RAM memory, or a stable memory (non-volatile memory), such as a magnetic disk memory. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

Optionally, the route navigation device may also include a camera, RF (Radio Frequency, radio frequency) circuits, sensors, audio circuits, WiFi modules, etc. Among them, sensors such as light sensors, motion sensors and other sensors. Specifically, the light sensor may include a proximity sensor, where the proximity sensor may control the vehicle to stop when the movement path navigation device moves to an obstacle.

Those skilled in the art can understand that the structure of the route navigation device shown in FIG. 1 does not constitute a limitation on the route navigation device, and may include more or fewer components than those shown in the figure, or a combination of certain components, or different components. Layout.

As shown in FIG. 1, the memory 1005, which is a computer storage medium, may include an operating system, a network communication module, a user interface module, and a route navigation program.

In the route navigation device shown in FIG. 1, the network interface 1004 is mainly used to connect to the back-end server and communicate with the back-end server; the user interface 1003 is mainly used to connect to the client (user side) and communicate with the client; and The processor 1001 may be used to call a route navigation program stored in the memory 1005.

In this embodiment, the path navigation device includes: a memory 1005, a processor 1001, and a path navigation program stored on the memory 1005 and running on the processor 1001, wherein the processor 1001 calls the memory 1005 to store When the route navigation program, and perform the following operations in the various embodiments of the vehicle navigation method.

The present application also provides a vehicle navigation method. Referring to FIG. 2, FIG. 2 is a schematic flowchart of the first embodiment of the vehicle navigation method of this application.

The vehicle navigation method of this embodiment can be applied to the process of intelligent automatic driving, where intelligent automatic driving can be applied to warehouse freight in a closed environment and also applicable to road transportation in an open environment. This embodiment takes warehouse freight as an example for illustration; The vehicle corresponding to warehouse freight can be a forklift, a truck, or an AGV (Automated Guided Vehicle, automatic guided transport vehicle) trolley and other equipment that can realize the transportation of goods; goods are stacked in warehouse freight, and the goods are placed on pallets, and the vehicle realizes the transportation of goods by transporting the pallets. It is understandable that a preset identification line is preset on the floor of the warehouse, and the driving route of the vehicle is formed between two adjacent and parallel preset identification lines.

The vehicle navigation method includes:

Step S100, when it is determined that the vehicle is located at the first designated location corresponding to the target storage location based on the current first location information of the vehicle, obtain the origin of the coordinates corresponding to the vehicle;

In this embodiment, the vehicle is equipped with a lidar, and the position information of the vehicle can be obtained in real time through the lidar. At the same time, if the vehicle is on the way of accessing goods, the target location corresponding to the vehicle is obtained, that is, the goods to be stored or the goods to be picked up. The first designated location corresponding to the target warehouse is determined according to the preset rules for the location where the vehicle is located. The vehicle can rotate at the first designated location to match the target location, and the first designated location is based on The target location, the length and width of the vehicle are determined.

Then, based on the first position information, it is determined whether the vehicle is located at the first designated position, that is, whether the vehicle currently reaches the first designated position, and when the vehicle is at the first designated position, the coordinate origin corresponding to the vehicle is obtained, for example, the vehicle For forklifts that carry pallets, the center position (near) of the rear axle of the forklift is the origin of the coordinates (center of the circle) corresponding to the vehicle.

Step S200, controlling the rotation of the vehicle based on the coordinate origin, and determining whether the edge marking line corresponding to the target storage location is perpendicular to the vehicle based on the first ground image currently captured by the camera installed on the vehicle;

In this embodiment, after the origin of the coordinates is determined, the vehicle is controlled to rotate according to the origin of the coordinates. Specifically, when the camera device is installed on the left side of the vehicle, the vehicle is controlled to rotate clockwise, and the camera device is installed on the right side of the vehicle. When turning, control the vehicle to rotate counterclockwise.

During the rotation of the vehicle, an image is taken in real time by the camera installed on the vehicle to obtain the corresponding first ground image, and the first ground image is used to determine whether the edge marking line corresponding to the target location is perpendicular to the vehicle. The device is a depth camera.

Specifically, in this embodiment, the camera device includes two camera devices, and the two camera devices are respectively arranged in the front and the side of the vehicle,

3, in an embodiment, step S200 includes:

Step S210: Acquire a first ground image currently captured by the camera device, and identify the initial position of each identification element in the first ground image;

Step S220: Separate the ground feature area from the first ground image, and determine the centroid position of the target element in each of the identification elements according to the ground feature area and each of the initial positions;

Step S230: Determine the depth data coordinates of each target element according to each of the centroid positions, and determine the first target straight line equation corresponding to the edge identification line according to each of the depth data coordinates;

Step S240: Determine whether the edge identification line is perpendicular to the vehicle based on the first target straight line equation.

In this embodiment, during the rotation of the vehicle, the image is taken in real time by the camera installed on the vehicle to obtain the corresponding first ground image. Understandably, the edge markings of the storage locations in the warehouse are actually pasted on the ground. The tape on the top is usually composed of diamond-shaped blocks with two colors spaced apart from each other, such as black diamond-shaped blocks with yellow diamond-shaped blocks, black diamond-shaped blocks with white diamond-shaped blocks, etc.

Then, the first ground image is subjected to background processing, and each identification element is extracted from the background-processed first ground image; each of the identification elements is sequentially processed by edge extraction, contour search, and polyline fitting. , Obtain the initial contour of each of the identification elements; transmit each of the initial outlines to a preset function, and determine the initial coordinates of each of the identification elements in the ground image; take each of the initial coordinates as the center of the circle, and set Defining a circular area, and identifying each of the circular areas as the initial position of each identification element in the ground image.

Further, the first ground image is stripped of the background by flood filling, and 8-10 multi-color seeds are preset to fill the first ground image to remove other substances in the first ground image; wherein The seed is set according to actual requirements. For example, the vertices of the four corners in the first ground image and the third halves of the edge of the first ground image can be set, which is not limited. Since then, combined with OpenCV (Open Source Computer Vision Library, an open source computer vision library) is used to realize the preset function of HSV (hue, saturation, value, hue, color saturation, value) color recognition, and extract the black diamond block as the identification element.

Further, call the preset function used to extract the edge in OpenCV, set the edge range parameters and transfer to the preset function, and perform edge extraction on the extracted identification elements; when the edge size of a certain identification element is in the edge range Within the parameters, the edge extraction operation is performed on the identification element to obtain the edge pixels formed by each black diamond block in the first ground image; when the edge size of a certain identification element is not within the edge range parameters, no edge extraction is performed on it Operation, and remove it as interference. After that, the preset function for contour search in OpenCV is called, the parameters of the set contour range are transferred to the preset function, and the contour search is performed on each identification element on the basis of edge extraction; when the contour size of a certain identification element is in Within the contour range parameter, the contour of the identification element is retained to obtain its contour point; when the contour size of a certain identification element is not within the contour range parameter, its contour is removed to remove the first ground image Interfere with contours. After each identification element undergoes edge extraction and contour search to obtain the contour points of each identification element that meets the requirements, the contour points of each identification element are processed by polyline fitting to obtain the initial contour of each identification element.

In addition, this embodiment has a pre-established three-dimensional space coordinate system. The three-dimensional space coordinate system uses the position of the stereo camera as the coordinate origin, the plane where the AGV car is located is the XY plane, and the upper space perpendicular to the XY plane is the positive direction of the Z axis. Space; where for the XY plane, the direction of the X axis is the direction directly in front of the vehicle and the direction perpendicular to the X axis on the right side of the vehicle is the Y axis. After the initial contour of each representative element is obtained, the preset function used to calculate the centroid position in OpenCV is called, the initial contour of each identification element is transferred to the preset function, and the coordinate value is output through the processing of the preset function. The coordinate value is the initial coordinate of each identification element in the first ground image. Thereafter, the preset radius value is called, and the circular area corresponding to each identification element is set with the initial coordinate as the center of the circle, and the circular area is the initial position of the identification element in the first ground image.

Understandably, there may be obstacles in the path of the vehicle. The obstacles are imaged in the first ground image, resulting in interference signals that are misidentified as identification elements; in order to avoid interference from interference signals, a ground feature region extraction mechanism is provided . The ground feature area is the area occupied by the ground image in the first ground image. Because the obstacle has a certain projection height on the Z axis of the three-dimensional space coordinate system, a certain projection threshold can be set to identify the first ground image And remove the identified obstacles from the first ground image to obtain the ground feature area.

Then, the coordinate origin in the three-dimensional space coordinate system is used as the preset coordinate origin, and the ground feature area and each initial position are generated according to the three-dimensional space coordinate system. Based on the preset coordinate origin, the image and The images representing each initial position are processed to determine the target element in each identification element and the centroid coordinates of each target element. Specifically, according to a preset coordinate origin, the ground feature area and each of the initial positions are combined, and the overlapping feature area between the ground feature area and each of the initial positions is extracted; and each of the overlapping feature areas is It is transmitted to a preset model, the target elements in each of the identification elements are screened out, and the element coordinates of each of the target elements are calculated as the centroid position of each of the target elements.

Call the preset model, and transfer each overlapping feature area to the preset model, classify the features of each overlapping feature area, and filter out the areas that meet the ground features and have black blocks, and this area is the identification element The target element that meets the characteristics of the black diamond block. At the same time, the preset model has the function of calculating the coordinates of the filtered area, and the element coordinates of each target element are obtained through the calculation function; the element coordinates are essentially the centroid coordinates of the target element, which is taken as the centroid position of the target element.

Then, after obtaining the centroid position of each target element, combine the installation parameters of the stereo camera to perform polar coordinate conversion on the centroid coordinates representing the centroid position to obtain the depth data coordinates of each target element to fit the first target according to the depth data coordinates Straight line equation, the ground restoration identification line is generated from the first target straight line equation. Considering that during the imaging process of the stereo camera, there may be holes in the first ground image due to its own characteristics, reflection, absorption, refraction and other factors. The depth data coordinates cannot be obtained during the conversion of the hole data, which leads to the failure of the polar coordinate conversion. It is necessary to perform preprocessing between the conversions to fill the hole data. Specifically, the hole data in the ground feature area is detected one by one, and the peripheral depth data corresponding to the hole data is read; the hole data is filled according to the peripheral depth data until the ground feature area The hole data in are all filled, so as to determine the depth data coordinates based on the filled ground feature area.

Scan the ground feature area, and detect the hole data one by one. Whenever the hole data is detected, the other data around it is read as the peripheral depth data corresponding to the detected hole data, and the peripheral depth data is used to pair with the peripheral depth data through the expansion algorithm. The hole data is expanded in the neighborhood to realize the filling of the hole data. All the hole data in the ground feature area are filled, and then on the basis of the filled ground feature area, the polar coordinate conversion of each centroid coordinate can be performed to obtain the depth data coordinates of each target element. After that, the preset algorithm is called to calculate the converted depth data coordinates to identify the edge identification line in the first ground image; specifically, the target of each depth data coordinate is determined according to the preset range interval Data coordinates, and generate a first target straight line equation according to each of the target data coordinates.

Further, the preset algorithm in this embodiment is preferably the least squares method. The circular area as the initial position of the target element is taken as the preset range interval, and the depth data coordinates of each target element are based on the preset range interval. Points adjacent to the front, back, left, and right. Whenever the front and back or left and right points are found, the three points are removed and saved in an array as the target coordinate data of each depth data coordinate. After finding the target coordinate data for each depth data coordinate, the least square method is used to generate each target coordinate data into the first target straight line equation, and the straight line corresponding to the first target straight line equation is the edge identification line in the first ground image Location. By initially identifying the initial position of the marking element in the edge marking line, and then accurately identifying its precise centroid position on the basis of eliminating interference, the depth data coordinates determined by the centroid position accurately reflect the position of each marking element, which improves Accuracy of edge identification line recognition.

Then, it is determined whether the edge identification line is perpendicular to the vehicle based on the first target straight line equation, the straight line equation of the vehicle can be determined, and the edge is determined according to the first target straight line equation of the edge identification line and the straight line equation of the vehicle Whether the identification line is perpendicular to the vehicle.

Step S300, when the edge marking line is perpendicular to the vehicle, control the vehicle to stop rotating.

In this embodiment, when the edge marking line is perpendicular to the vehicle, the vehicle has rotated to the designated storage point. At this time, the vehicle is controlled to stop rotating to match the vehicle with the target storage location, which is convenient for subsequent direct reverse linear movement Vehicles so that the vehicles can be accurately stored.

It should be noted that this embodiment is applied to a scene where vehicles move in a narrow lane between multiple storage locations, so that the vehicle moves quickly, usually the narrow lane width L≥the forklift diagonal length + 0.2 meters; the storage location width l ≥ pallet width + 0.1 meters; for example, in this embodiment, the forklift length = 1.8 meters, the pallet width = 1 meter, and the size of the storage location: aisle L = 2 meters, and storage location l = 1.1 meters.

Referring to Figure 4, in Figure 4, 1.1-1.3 are the position of the origin of the vehicle's coordinates, 2.1 is the direction of movement of the vehicle; 2.2 is the trajectory of the vehicle. The dotted line is the ground marking line of the storage location, including parallel yellow and black warning lines and yellow and black edge markings at the entrance (exit) of the storage location. When the coordinate origin of the vehicle is at the first designated position 1.1, the vehicle starts to rotate according to the direction of movement shown in 2.1, and the edge marking line is perpendicular to the vehicle, that is, when the vehicle rotates 90 degrees, the rotation stops.

In an embodiment, the camera includes two camera devices, and the two camera devices are respectively arranged in front of and on the side of the vehicle. Step S230 includes:

Step a: According to each of the depth data coordinates, determine a first straight line equation of the edge identification line corresponding to a front camera device, and a second straight line equation of the edge identification line corresponding to a side camera device;

Step b: Perform fusion based on the first straight line equation and the second straight line equation to obtain the first target straight line equation.

Since the camera device includes two depth cameras respectively arranged in the front and the side of the vehicle, the first ground image includes the front ground image and the side ground image, and the edge identification line corresponding to the front camera device can be obtained according to the front ground image. The first straight line equation, and the second straight line equation that obtains the edge identification line corresponding to the side camera device according to the side ground image, and then the coordinate system where the first straight line equation is located and the coordinate system where the second straight line equation is located are merged , The fusion is specifically performed according to the fusion filtering algorithm, and the fused coordinate system and the first target straight line equation in the fused coordinate system are obtained.

Among them, if there is only one straight line equation in the coordinate system after fusion, then the straight line equation in the fused coordinate system is the first target straight line equation needed. If there are two straight line equations in the fused coordinate system, and two If the straight line equation is vertical, it means that the vertical ratio of the two straight line equations is the yellow and black warning line of the target storage location and the edge marking line of the storage location entrance. The straight line equation with the largest angle between the straight line equations is the first target straight line equation.

The vehicle navigation method proposed in this embodiment obtains the coordinate origin corresponding to the vehicle when it is determined based on the current first position information of the vehicle that the vehicle is located at the first designated location corresponding to the target storage location; and then based on the coordinate origin Control the rotation of the vehicle, and determine whether the edge identification line corresponding to the target storage location is perpendicular to the vehicle based on the first ground image currently captured by the camera installed on the vehicle; When the vehicle is vertical, the vehicle is controlled to stop rotating, and when moving in the narrow lane corresponding to the vehicle location, the vehicle is perpendicular to the edge marking line of the target location by rotating the vehicle, so that the vehicle and the target location can be accurately aligned. In order to make the vehicle enter the target location accurately and quickly, and improve the efficiency of vehicle navigation.

Based on the first embodiment, a second embodiment of the vehicle navigation method of the present application is proposed. Referring to FIG. 5, in this embodiment, before step S200, the vehicle navigation method further includes:

Step S400, acquiring a second ground image based on the camera device, and determining a relative position parameter between the vehicle and a preset identification line according to the second ground image;

Step S500, reading the historical ground image acquired based on the camera device, and determining the displacement parameter of the vehicle according to the second ground image and the historical ground image;

Step S600: Determine a position adjustment parameter according to the relative position parameter, and use the position adjustment parameter and the displacement parameter as posture adjustment parameters to adjust the posture of the vehicle.

During the driving of the vehicle, the stereo camera photographs and images the side ground in the driving direction in real time, and generates a second ground image that characterizes the relative position between the vehicle and the preset marking line. If the driving path of the vehicle deviates, the relative position between the vehicle and the preset identification line also deviates, so that the preset identification line in the second ground image deviates. The preset identification line is a straight line corresponding to the edge identification line of the target storage location.

In order to determine whether the preset marking line in the second ground image is deviated, a three-dimensional space coordinate system is established based on the current position of the vehicle, the position of the stereo camera is taken as the coordinate origin, and the plane where the vehicle is located is the XY plane, which is compared with the XY plane. The vertical upper space is the space where the positive direction of the Z-axis is located; among them, for the XY plane, the direction directly in front of the vehicle is the X-axis direction, and the direction perpendicular to the X-axis direction on the right side of the vehicle is the Y-axis direction.

According to the position of the preset identification line in the second ground image, the linear equation of the preset identification line on the XY plane is determined, and the relative position parameter of the vehicle relative to the preset identification line is determined. The relative position parameter includes the relative position of the vehicle. For the angle and distance of the preset identification line, the passing angle indicates whether the vehicle is parallel to the preset identification line, and the passing distance indicates whether the distance between the vehicle and the preset identification line on the left and right sides is equal. Specifically, the straight line equation corresponding to the preset identification line is obtained, and the slope of the straight line equation is calculated; the driving direction of the vehicle is taken as the reference direction, and the straight line equation and the reference are calculated according to the slope. The included angle between directions; according to the straight line equation, the distance between the vehicle and the preset identification line is calculated, and the included angle and the distance are determined as the relative position parameter.

Understandably, the preset marking line is essentially a pattern composed of rhombuses with yellow and black intervals or black and white intervals. After the second ground image is obtained, image processing is performed on it, and the black rhombuses are extracted, and each black is determined. The position of the center of mass of the rhombus; fitting the position of the center of mass to generate a straight line equation, which is the straight line where the preset marking line is located. After that, the slope of the linear equation is calculated.

Further, the driving direction of the vehicle is taken as the reference direction, and the angle between the linear equation and the reference direction is calculated based on the slope. Since the negative direction of travel in the three-dimensional space coordinate system is the positive direction of the x-axis, the reference direction is essentially the direction of the x-axis, and the calculated included angle is the included angle between the preset marking line and the x-axis, that is, the vehicle travel direction and the preset Identify the angle between the lines. At the same time, the distance between the vehicle and the preset marking line is calculated according to the parameters of the straight line equation; the angle △α is calculated by the formula △α=tan k, and the distance △L is calculated by the formula △L= /(A +B) Calculation. Thereafter, the calculated included angle and distance are determined as relative position parameters to determine whether the posture of the vehicle needs to be adjusted through the relative position parameters.

Furthermore, the historical ground image acquired by the camera device at the previous moment is read, and the relative position change of the vehicle is reflected by the comparison between the historical ground image at the previous moment and the second ground image, thereby determining the displacement parameter of the vehicle .

Understandably, in order to determine whether the vehicle is parallel to the preset identification line and the distance to the preset identification lines on both sides is equal, a preset included angle and a preset distance are preset. Compare the included angle in the relative position parameter with the preset included angle to get the angle difference between the two. The angle difference is used to characterize the difference between the actual angle and the theoretical angle of the vehicle. The smaller the difference, the smaller the difference between the vehicle and the theoretical angle. The parallelism between the preset marking lines is better; at the same time, the distance in the relative position parameter is compared with the preset distance to obtain the distance difference between the two. The distance difference is used to characterize the actual distance between the vehicle and the theoretical distance. The size of the difference between the two, the smaller the difference, the greater the possibility that the distance between the vehicle and the preset signs on both sides is equal.

The angle difference and distance difference obtained through the comparison are determined as the position adjustment parameters, and the position adjustment parameters and the displacement parameters are used as the attitude adjustment parameters to adjust the angle of the vehicle position and the preset marking line on both sides Adjust the attitude of the distance between the two, and calculate the displacement of the vehicle at the front and rear moments; while avoiding collisions with the goods stacked on both sides, the displacement distance is calculated to determine the driving distance to the destination.

Further, the posture adjustment of the vehicle can be adjusted through the control center of the vehicle, or through an upper computer connected to the vehicle in communication. Specifically, when the upper computer is used for adjustment, the vehicle sends the position adjustment parameters and displacement parameters as the attitude adjustment parameters to the upper computer; the upper computer adjusts the driving angle of the vehicle according to the angle difference represented by the angle difference. According to the distance difference represented by the distance difference, the left and right positions of the vehicle are adjusted. At the same time, the displacement distance of the vehicle from the previous moment to the current moment is calculated according to the displacement parameter; the displacement distance is used to update the driving distance of the vehicle to represent the vehicle The distance to the destination. The host computer will determine whether to adjust or not, and the adjusted parameters will be sent to the vehicle to control the driving state of the vehicle and realize the precise transportation of the vehicle.

When the vehicle's control center adjusts the attitude of the vehicle, the control center directly adjusts the driving angle of the vehicle according to the angle difference represented by the angle difference, and adjusts the vehicle's driving angle according to the distance difference represented by the distance difference. The left and right positions are adjusted, and the displacement distance of the vehicle from the last moment to the current moment is calculated according to the displacement parameters. The displacement distance is used to update the travel distance of the vehicle, which represents the distance between the vehicle and the destination; in this way, the vehicle is controlled The driving state of the vehicle can realize the accurate transportation of the vehicle.

Further, step S500 includes: identifying the first data point in the second ground image and the second data point in the historical ground image, and filtering out the first coordinate point and the second data point in each of the first data points. The second coordinate point in each of the second data points; the first center coordinates in each of the first coordinate points and the second center coordinates in each of the second coordinate points are determined respectively, and according to the first The center coordinates and the second center coordinates determine the displacement parameters of the vehicle.

Further, the displacement parameters used to calculate the displacement distance include displacement value and displacement angle, where the displacement value is the distance value between the position of the vehicle at the previous moment and the position point of the current moment, and the displacement angle is the distance between the vehicle and the driving direction , That is, the included angle in the x-axis direction. In this embodiment, when determining the displacement parameters, first extract the black diamond blocks of the preset marking line in the second ground image, identify the centroid of each black diamond block, and determine each centroid as the first data in the second ground image Point; At the same time, extract the black diamond blocks of the preset marking line in the historical ground image, identify the centroid of each black diamond block, and determine each centroid as the second data point in the historical ground image. After that, for the first data point, filter according to the straight line equation of the preset identification line in the second ground image, and determine the point belonging to the straight line equation as the first coordinate point; at the same time, for the second data point, according to the preset The line equation of the marking line in the historical ground image is screened, and the point belonging to the line equation is determined as the second coordinate point. It should be noted that the slopes of the two linear equations are within the preset range. If it exceeds the preset range, it means that the vehicle has a large displacement at the front and rear moments and an abnormal situation has occurred. At this time, the displacement of the vehicle is monitored on the one hand, and the other Regenerate the linear equation to ensure the correctness of the calculation.

Further, the first coordinate point and the second coordinate point are screened, and the valid points in the historical ground image and the second ground image are determined, and the first center in the first coordinate point is determined by the respective valid points. Coordinates and the second center coordinates in the second coordinate point. Specifically, according to each of the second coordinate points, a first effective point corresponding to each of the first coordinate points is determined, and the averaging process is performed on each of the first effective points to determine the first center coordinate; For each of the first coordinate points, a second effective point corresponding to each of the second coordinate points is determined, and average processing is performed on each of the second effective points to generate the second center coordinate.

When determining the first center coordinates of each first coordinate point, use each second coordinate point as a basis to filter out the point with the closest distance to each first coordinate point from each second coordinate point; after that, the closest distance to each first coordinate point is selected. The point is used as the first effective point to perform the average value processing of the coordinate values, and the average value obtained is the first center coordinate corresponding to each first coordinate point. If the first coordinate point contains a1 (x1, y1), a2 (x2, y2), a3 (x3, y3), a4 (x4, y4)•••an(xn, yn) N points, the first point is determined by searching Among the two coordinate points, the point closest to a1 is b1, the point closest to a2 is b2, the point closest to a3 is b3, the point closest to a4 is b4, and the point closest to an is bn; The coordinate values of b1, b2, b3, b4•••bn are averaged, and the average value (x, y) of the coordinate values is obtained. The average value (x, y) is the first center of each first coordinate point coordinate.

Similarly, when determining the second center coordinates of each second coordinate point, use each first coordinate point as a basis to filter out the point with the closest distance to each second coordinate point from each first coordinate point; The closest point is used as the second effective point to perform the average value processing of the coordinate values, and the average value obtained is the second center coordinate corresponding to each second coordinate point.

Further, according to the first center coordinate and the second center coordinate, the displacement value and the displacement angle in the displacement parameter can be calculated. Specifically, according to the first center coordinates and the second center coordinates, calculate the slope of the straight line formed by the first center coordinates and the second center coordinates, and calculate the relative displacement value of the vehicle; The slope of the straight line calculates the displacement angle of the vehicle, and the relative displacement value and the displacement angle are determined as the displacement parameters of the vehicle.

Furthermore, (x1, y1) are the first center coordinates, (x0, y0) are the second center coordinates, a straight line is formed between the first center coordinates and the second center coordinates, passing through the first center coordinates and the second center coordinates The slope of the straight line formed is calculated, and the angle corresponding to the slope reflects the angle change of the vehicle relative to the preset marking line at the front and back two moments. At the same time, the first center coordinate and the second center coordinate also reflect the displacement of the vehicle at the front and rear moments, so that the relative displacement value of the vehicle can be calculated through the first center coordinate and the second center coordinate. The formula for calculating the slope k is: k=(y1-y2)/(x1-x0), and the formula for calculating the relative displacement value △S is: △S=((x1-x0) +(y1-y0)).

Further, the displacement angle of the vehicle is calculated by the slope k, which is the angle change of the vehicle relative to the preset marking line at two moments before and after; the calculation formula for the displacement angle ℬ is: ℬ = Tan k . The calculated relative displacement value and displacement angle are determined as the displacement parameters of the vehicle, so as to calculate the displacement distance traveled by the vehicle at two moments before and after the displacement parameters. Calculate the projection of the relative displacement value in the x-axis direction through the relative displacement value and displacement angle in the displacement parameter. The projected value is the displacement distance the vehicle travels along the direction of travel; and the displacement distance is used to compare the distance between the vehicle and the destination. The driving distance between the two is updated to achieve accurate transportation.

In the vehicle navigation method proposed in this embodiment, a second ground image is acquired based on the camera device, and the relative position parameter between the vehicle and a preset identification line is determined according to the second ground image; The historical ground image acquired by the camera device determines the displacement parameter of the vehicle according to the second ground image and the historical ground image; then the position adjustment parameter is determined according to the relative position parameter, and the position adjustment parameter And the displacement parameter is used as the attitude adjustment parameter to adjust the attitude of the vehicle. Because the attitude adjustment parameter used to realize the adjustment is generated according to the relative position parameter and the displacement parameter of the vehicle, it can accurately characterize the displacement change of the vehicle, and realize The accurate adjustment of the vehicle posture is conducive to accurate transportation.

Based on the first embodiment, a third embodiment of the vehicle navigation method of the present application is proposed. In this embodiment, before step S200, the vehicle navigation method further includes:

Step S700: Determine the marking lines on both sides of the target storage location based on the third ground image currently captured by the camera device;

Step S800: Control the vehicle to move in the reverse direction based on the marking lines on both sides, and control the vehicle to stop moving when the rear stop line is monitored or it is determined that the anti-collision sensor currently detects the cargo, wherein the anti-collision sensor Installed at the end of the vehicle.

Among them, the vehicle is a forklift, and the forklift is equipped with two anti-collision sensors, which are respectively installed at the end of the fork of the forklift. When the fork is lifted, it can detect the pallet cargo at a specified distance behind, and it can be inserted when the fork is down. Pallet anti-collision detection.

In this embodiment, when the vehicle stops rotating, based on the third ground image currently captured by the camera device, the identification lines on both sides of the target location are determined, wherein the determination method of the identification lines on both sides is the same as that of the edge identification lines. The determination method is similar. First, the straight line equations of the identification lines on both sides are determined, the identification lines on both sides are determined according to the straight line equation, and then the vehicle is controlled to move in the reverse direction based on the identification lines on both sides, so that the vehicle can move to the target storage location. During the reverse movement of the vehicle, the ground image captured by the camera device and the detection result of the collision avoidance sensor are collected in real time, and the rear stop line is determined according to the ground image captured by the camera device, or according to the detection result of the collision avoidance sensor The detection result determines that when the anti-collision sensor currently detects goods, the vehicle is controlled to stop moving.

It is understandable that when the vehicle stops rotating, the steps in the second embodiment can be executed first to realize the posture adjustment of the vehicle.

The vehicle navigation method proposed in this embodiment determines the identification lines on both sides of the target location based on the third ground image currently captured by the camera; and then controls the vehicle to move in the reverse direction based on the identification lines on both sides , And when the rear stop line is monitored or it is determined that the anti-collision sensor currently detects the goods, the vehicle is controlled to stop moving, wherein the anti-collision sensor is installed at the end of the vehicle to realize the accurate movement of the vehicle in the warehouse , To further improve the navigation efficiency of the vehicle.

Based on the first embodiment, a fourth embodiment of the vehicle navigation method of the present application is proposed. In this embodiment, after step S100, the vehicle navigation method further includes:

Step c, determining whether the vehicle satisfies a U-turn condition based on the first location information and the target storage location;

Step d, if it is not met, execute the step of acquiring the origin of the coordinates corresponding to the vehicle when it is determined based on the first location information that the vehicle is located at the first designated location corresponding to the target storage location.

In this embodiment, when the first location information is acquired, it is determined whether the vehicle meets the U-turn condition based on the first location information and the target location, and specifically the moving direction of the vehicle is determined based on the first location information. The moving direction and the target location determine whether the vehicle currently needs to move to the other side of the warehouse, and if not, execute step S200.

Further, in an embodiment, after step c, it further includes:

Step e, if it is satisfied, determine a second designated location corresponding to the vehicle based on the current location information;

Step f, controlling the vehicle based on the second designated position;

Step g, when the current second position information of the vehicle determines that the vehicle is located at the second designated position, control the rotation of the vehicle based on the origin of the second coordinate corresponding to the vehicle;

Step h, when the vehicle rotates to a third designated position corresponding to the target storage location, control the vehicle to stop rotating.

In this embodiment, if the vehicle satisfies the U-turn condition, the second designated position corresponding to the vehicle is determined based on the current position information, and the vehicle is controlled based on the second designated position, so that the second designated position of the vehicle is moving. The designated location, where the second designated location can be set according to the target storage location, so that the vehicle can quickly reach the target storage location after turning around at the second specified location.

Then, when the current second position information of the vehicle determines that the vehicle is located at the second designated position, the vehicle is controlled to rotate based on the origin of the second coordinate corresponding to the vehicle, even if the vehicle rotates 180 degrees, a U-turn of the vehicle is realized, And when the vehicle rotates to the third designated position corresponding to the target storage location, that is, when the vehicle completes a U-turn operation, the vehicle is controlled to stop rotating, thereby realizing a U-turn of the vehicle.

It is understandable that when the current second position information of the vehicle determines that the vehicle is located at the second designated position, the steps in the third embodiment can be executed to adjust the vehicle's posture.

The vehicle navigation method proposed in this embodiment determines whether the vehicle satisfies the U-turn condition based on the first location information and the target location, and then if it is not met, then executes the determination that the vehicle is located based on the first location information. When the target location corresponds to the first designated location, the step of obtaining the coordinate origin corresponding to the vehicle, and then execute the subsequent steps when the vehicle does not need to turn around, so as to realize the accurate navigation of the vehicle and further improve the navigation efficiency of the vehicle.

Based on the foregoing embodiments, a fifth embodiment of the vehicle navigation method of the present application is proposed. In this embodiment, the vehicle navigation method further includes:

Step i: When it is determined that the vehicle is in a narrow-track linear movement state based on the current third position information of the vehicle and the navigation path corresponding to the vehicle, acquire the fourth ground image currently captured by the camera device, and identify the first 4. The initial position of each identification element in the ground image;

Step j: Separate the ground feature area from the fourth ground image, and determine the centroid position of the target element in each of the identification elements according to the ground feature area and each of the initial positions;

Step k: Determine the depth data coordinates of each target element according to each of the centroid positions, and according to each of the depth data coordinates;

Step 1. Identify the second target straight line equation corresponding to the edge identification line in the fourth ground image according to each of the depth data coordinates, and determine the calibration position of the vehicle based on the second target straight line equation;

Step m: Determine the target position and attitude information of the vehicle based on the calibration position, and control the vehicle based on the target position and the attitude information.

In this embodiment, when it is determined that the vehicle is in a narrow-track linear movement state based on the current third position information of the vehicle and the navigation path corresponding to the vehicle, the fourth ground image currently captured by the camera device is acquired, and the fourth ground image is acquired according to the first The fourth ground image determines the second target straight line equation corresponding to the edge identification line in the fourth ground image, where the narrow-track linear movement state refers to the driving state of the vehicle moving linearly in the narrow lane between the two ground stack warehouses, specifically , Determining that the vehicle is in a narrow lane according to the third location information and the navigation path corresponding to the vehicle, and determining that the vehicle needs to move in a straight line according to the third location information and the target location, the vehicle is in a state of straight moving in the narrow lane, The method for determining the second target straight line equation corresponding to the edge identification line in the fourth ground image is similar to the method for determining the first target straight line equation in the foregoing embodiment, and will not be repeated here.

Then, the calibration position of the vehicle is determined based on the second target straight line equation; and the target position and attitude information of the vehicle are determined based on the calibration position, and the vehicle is controlled based on the target position and the attitude information , In order to realize the straight line movement of the vehicle in the narrow lane.

Further, the camera device includes two camera devices, the two camera devices are respectively arranged in the front and the side of the vehicle, and the edge marking line includes, according to each of the depth data coordinates, identifying in the ground image The steps of the second target straight line equation corresponding to the edge identification line include:

The third straight line equation of the edge identification line corresponding to the front camera device and the fourth straight line equation of the edge identification line corresponding to the side camera device are determined according to each of the depth data coordinates; based on the third The straight line equation and the fourth straight line equation are fused to obtain the second target straight line equation.

Since the camera device includes two depth cameras respectively arranged in the front and the side of the vehicle, the first ground image includes the front ground image and the side ground image, and the edge identification line corresponding to the front camera device can be obtained according to the front ground image. The first straight line equation, and the second straight line equation that obtains the edge identification line corresponding to the side camera device according to the side ground image, and then the coordinate system where the first straight line equation is located and the coordinate system where the second straight line equation is located are merged , The fusion is specifically performed according to the fusion filtering algorithm, and the fused coordinate system and the second target straight line equation in the fused coordinate system are obtained.

Among them, if there is only one linear equation in the coordinate system after the fusion, the coordinate origin in the coordinate system after the fusion is the calibration position. If there are two linear equations in the coordinate system after the fusion, and the two linear equations are perpendicular, then The intersection of the two straight line equations is the calibration position.

The vehicle navigation method proposed in this embodiment acquires the fourth ground currently photographed by the camera device when it is determined that the vehicle is in a state of linear movement in a narrow lane based on the current third position information of the vehicle and the navigation path corresponding to the vehicle. Image, and identify the initial position of each identification element in the fourth ground image; then separate the ground feature area from the fourth ground image, and determine each location based on the ground feature area and each of the initial positions The position of the center of mass of the target element in the identification element; then according to the position of the center of mass, the depth data coordinates of each of the target elements are determined, and according to each of the depth data coordinates; and then according to each of the depth data coordinates, the The second target straight line equation corresponding to the edge identification line in the ground image, and the calibration position of the vehicle is determined based on the second target straight line equation; finally, the target position and attitude information of the vehicle are determined based on the calibration position, and The vehicle is controlled based on the target position and the posture information, and then when the vehicle is in a narrow lane linear movement state, the vehicle’s posture is adjusted and the vehicle is controlled according to the target position to achieve rapid linear movement of the vehicle in the narrow lane. Further improve the efficiency of vehicle navigation.

In addition, an embodiment of the present application also proposes a computer-readable storage medium having computer-readable instructions stored on the computer-readable storage medium, and when the computer-readable instructions are executed by a processor, any of the foregoing The steps of the vehicle navigation method.

The specific embodiments of the computer-readable storage medium of the present application are basically the same as the embodiments of the vehicle navigation method described above, and will not be described in detail here.

It should be noted that in this article, the terms "include", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements not only includes those elements, It also includes other elements not explicitly listed, or elements inherent to the process, method, article, or system. Without more restrictions, the element defined by the sentence "including a..." does not exclude the existence of other identical elements in the process, method, article, or system that includes the element.

The serial numbers of the foregoing embodiments of the present application are only for description, and do not represent the advantages and disadvantages of the embodiments.

Through the description of the above implementation manners, those skilled in the art can clearly understand that the above-mentioned embodiment method can be implemented by means of software plus the necessary general hardware platform, of course, it can also be implemented by hardware, but in many cases the former is better.的实施方式。 Based on this understanding, the technical solution of this application essentially or the part that contributes to the existing technology can be embodied in the form of a software product, and the computer software product is stored in a storage medium (such as ROM/RAM) as described above. , Magnetic disks, optical disks), including several instructions to make a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) execute the method described in each embodiment of the present application.

The above are only the preferred embodiments of the application, and do not limit the scope of the patent for this application. Any equivalent structure or equivalent process transformation made using the content of the description and drawings of the application, or directly or indirectly applied to other related technical fields , The same reason is included in the scope of patent protection of this application.

Claims

A vehicle navigation method, wherein the vehicle navigation method includes the following steps:

It is determined based on the current first location information of the vehicle that the vehicle is located at the first designated location corresponding to the target storage location, and the origin of the coordinates corresponding to the vehicle is acquired; and,

Control the rotation of the vehicle based on the origin of the coordinates, and based on the first ground image currently captured by the camera installed on the vehicle, determine that the edge marking line corresponding to the target location is perpendicular to the vehicle, and control the vehicle to stop Spin.
The vehicle navigation method according to claim 1, wherein the first ground image currently captured by the camera installed on the vehicle is used to determine that the edge identification line of the target storage location corresponding to the first designated location is the same as that of the vehicle. The vertical steps include:

Acquiring a first ground image currently captured by the camera device, and identifying the initial position of each identification element in the first ground image;

Separating the ground feature area from the first ground image, and determining the centroid position of the target element in each of the identification elements according to the ground feature area and each of the initial positions;

Determine the depth data coordinates of each target element according to each of the centroid positions, and determine the first target straight line equation corresponding to the edge identification line according to each of the depth data coordinates; and,

It is determined that the edge identification line is perpendicular to the vehicle based on the first target straight line equation.
The vehicle navigation method according to claim 2, wherein the camera device includes two camera devices, and the two camera devices are respectively arranged in the front and the side of the vehicle, and the depth data coordinates are used to determine the The steps of the first target straight line equation corresponding to the edge identification line include:

According to each of the depth data coordinates, determine the first straight line equation of the edge identification line corresponding to the front camera device, and the second straight line equation of the edge identification line corresponding to the side camera device; and,

Fusion is performed based on the first straight line equation and the second straight line equation to obtain the first target straight line equation.
The vehicle navigation method according to claim 1, wherein before the step of controlling the rotation of the vehicle based on the coordinate origin, the method further comprises:

Acquiring a second ground image based on the camera device, and determining a relative position parameter between the vehicle and a preset identification line according to the second ground image;

Reading the historical ground image acquired based on the camera device, and determining the displacement parameter of the vehicle based on the second ground image and the historical ground image; and,

The position adjustment parameter is determined according to the relative position parameter, and the position adjustment parameter and the displacement parameter are used as the attitude adjustment parameter to adjust the attitude of the vehicle.
The vehicle navigation method according to claim 1, wherein, after the step of controlling the vehicle to stop rotating, the vehicle navigation method further comprises:

Determine the marking lines on both sides of the target storage location based on the third ground image currently captured by the camera device; and,

Control the vehicle to move in the reverse direction based on the identification lines on both sides, and monitor the rear stop line or determine that the anti-collision sensor currently detects goods, and control the vehicle to stop moving, wherein the anti-collision sensor is installed on the vehicle The end.
The vehicle navigation method according to claim 1, wherein, after the step of acquiring the current position information of the vehicle in real time, the vehicle navigation method further comprises:

It is determined based on the first location information and the target location that the vehicle does not meet the U-turn condition, and when it is determined that the vehicle is located at the first designated location corresponding to the target location based on the first location information, acquiring the vehicle corresponding The steps of the origin of the coordinates.
7. The vehicle navigation method of claim 6, wherein the vehicle navigation method further comprises:

If it is determined that the vehicle meets the U-turn condition based on the first location information and the target location, then determine the second designated location corresponding to the vehicle based on the current location information;

Controlling the vehicle based on the second designated position;

The current second position information of the vehicle determines that the vehicle is located at the second designated position, and controls the rotation of the vehicle based on the second coordinate origin corresponding to the vehicle; and,

The vehicle rotates to a third designated position corresponding to the target storage location, and the vehicle is controlled to stop rotating.
The vehicle navigation method according to claim 1, wherein the vehicle navigation method further comprises:

Based on the current third position information of the vehicle and the navigation path corresponding to the vehicle, it is determined that the vehicle is in a narrow-track linear movement state, the fourth ground image currently captured by the camera device is acquired, and each of the fourth ground images is identified Identify the initial position of the element;

Separating the ground feature area from the fourth ground image, and determining the centroid position of the target element in each of the identification elements according to the ground feature area and each of the initial positions;

Determine the depth data coordinates of each target element according to each of the centroid positions, and according to each of the depth data coordinates;

According to each of the depth data coordinates, identify the second target straight line equation corresponding to the edge identification line in the fourth ground image, and determine the calibration position of the vehicle based on the second target straight line equation; and,

The target position and attitude information of the vehicle are determined based on the calibration position, and the vehicle is controlled based on the target position and the attitude information.
The vehicle navigation method according to claim 8, wherein the camera device includes two camera devices, and the two camera devices are respectively arranged in front and the side of the vehicle, and the edge marking line includes, according to each of the For depth data coordinates, the step of identifying the second target straight line equation corresponding to the edge identification line in the ground image includes:

According to each of the depth data coordinates, determine the third straight line equation of the edge identification line corresponding to the front camera device, and the fourth straight line equation of the edge identification line corresponding to the side camera device; and,

Fusion is performed based on the third straight line equation and the fourth straight line equation to obtain the second target straight line equation.
The vehicle navigation method according to claim 2, wherein the vehicle navigation method further comprises:

Based on the current third position information of the vehicle and the navigation path corresponding to the vehicle, it is determined that the vehicle is in a narrow-track linear movement state, the fourth ground image currently captured by the camera device is acquired, and each of the fourth ground images is identified Identify the initial position of the element;

Separating the ground feature area from the fourth ground image, and determining the centroid position of the target element in each of the identification elements according to the ground feature area and each of the initial positions;

Determine the depth data coordinates of each target element according to each of the centroid positions, and according to each of the depth data coordinates;

According to each of the depth data coordinates, identify the second target straight line equation corresponding to the edge identification line in the fourth ground image, and determine the calibration position of the vehicle based on the second target straight line equation; and,

The target position and attitude information of the vehicle are determined based on the calibration position, and the vehicle is controlled based on the target position and the attitude information.
The vehicle navigation method according to claim 3, wherein the vehicle navigation method further comprises:

Based on the current third position information of the vehicle and the navigation path corresponding to the vehicle, it is determined that the vehicle is in a narrow-track linear movement state, the fourth ground image currently captured by the camera device is acquired, and each of the fourth ground images is identified Identify the initial position of the element;

Separating the ground feature area from the fourth ground image, and determining the centroid position of the target element in each of the identification elements according to the ground feature area and each of the initial positions;

Determine the depth data coordinates of each target element according to each of the centroid positions, and according to each of the depth data coordinates;

According to each of the depth data coordinates, identify the second target straight line equation corresponding to the edge identification line in the fourth ground image, and determine the calibration position of the vehicle based on the second target straight line equation; and,

The target position and attitude information of the vehicle are determined based on the calibration position, and the vehicle is controlled based on the target position and the attitude information.
The vehicle navigation method according to claim 4, wherein the vehicle navigation method further comprises:

Based on the current third position information of the vehicle and the navigation path corresponding to the vehicle, it is determined that the vehicle is in a narrow-track linear movement state, the fourth ground image currently captured by the camera device is acquired, and each of the fourth ground images is identified Identify the initial position of the element;

Separating the ground feature area from the fourth ground image, and determining the centroid position of the target element in each of the identification elements according to the ground feature area and each of the initial positions;

Determine the depth data coordinates of each target element according to each of the centroid positions, and according to each of the depth data coordinates;

According to each of the depth data coordinates, identify the second target straight line equation corresponding to the edge identification line in the fourth ground image, and determine the calibration position of the vehicle based on the second target straight line equation; and,

The target position and attitude information of the vehicle are determined based on the calibration position, and the vehicle is controlled based on the target position and the attitude information.
The vehicle navigation method according to claim 5, wherein the vehicle navigation method further comprises:

Based on the current third position information of the vehicle and the navigation path corresponding to the vehicle, it is determined that the vehicle is in a narrow-track linear movement state, the fourth ground image currently captured by the camera device is acquired, and each of the fourth ground images is identified Identify the initial position of the element;

Separating the ground feature area from the fourth ground image, and determining the centroid position of the target element in each of the identification elements according to the ground feature area and each of the initial positions;

Determine the depth data coordinates of each target element according to each of the centroid positions, and according to each of the depth data coordinates;

According to each of the depth data coordinates, identify the second target straight line equation corresponding to the edge identification line in the fourth ground image, and determine the calibration position of the vehicle based on the second target straight line equation; and,

The target position and attitude information of the vehicle are determined based on the calibration position, and the vehicle is controlled based on the target position and the attitude information.
A vehicle navigation device, wherein the vehicle navigation device includes a memory, a processor, and computer-readable instructions stored in the memory and capable of running on the processor, and the computer-readable instructions are When the processor executes, the following steps are implemented:

It is determined based on the current first location information of the vehicle that the vehicle is located at the first designated location corresponding to the target storage location, and the origin of the coordinates corresponding to the vehicle is acquired; and,

Control the rotation of the vehicle based on the origin of the coordinates, and based on the first ground image currently captured by the camera installed on the vehicle, determine that the edge marking line corresponding to the target location is perpendicular to the vehicle, and control the vehicle to stop Spin.
A computer-readable storage medium, wherein computer-readable instructions are stored on the computer-readable storage medium, and when the computer-readable instructions are executed by a processor, the following steps are implemented:

It is determined based on the current first location information of the vehicle that the vehicle is located at the first designated location corresponding to the target storage location, and the origin of the coordinates corresponding to the vehicle is acquired; and,

Control the rotation of the vehicle based on the origin of the coordinates, and based on the first ground image currently captured by the camera installed on the vehicle, determine that the edge marking line corresponding to the target location is perpendicular to the vehicle, and control the vehicle to stop Spin.