Method for positioning a vehicle, storage medium, vehicle positioning device and vehicle

Abstract

The present disclosure relates to a vehicle positioning method, a storage medium, a vehicle positioning device and a vehicle, the method comprising: obtaining point cloud information of a target area where the vehicle is located; determining a ground type of the target area according to the point cloud information; the ground type comprising a horizontal ground or an inclined ground; determining position information of the target vehicle according to the ground type and the point cloud information of the target area. In this way, by separately considering the vertical motion prediction of the vehicle on the horizontal ground and the inclined ground, the positioning drift of the vehicle in the vertical direction is avoided, and the accuracy of the cross-layer positioning of the vehicle in the multi-layer underground garage is improved.

Description

Technical Field

[0001] This disclosure relates to the field of vehicle control, and more specifically, to a method for vehicle positioning, a storage medium, a vehicle positioning device, and a vehicle. Background Technology

[0002] Underground parking garages often cannot receive GNSS (Global Navigation Satellite System) signals, have poor lighting conditions, narrow and complex roads, and most underground parking lots have multiple levels. These characteristics increase the difficulty and complexity of vehicle positioning.

[0003] For such scenarios, related technologies typically utilize measurement sensors such as wheel speedometers and IMUs (Inertial Measurement Units) to calculate the vehicle's state information for the next moment based on its motion state, thereby achieving vehicle positioning. However, this approach often exhibits significant drift in the vertical direction, resulting in insufficient vertical positioning accuracy. Summary of the Invention

[0004] To address the aforementioned problems, this disclosure provides a method for vehicle positioning, a storage medium, a vehicle positioning device, and a vehicle.

[0005] In a first aspect, this disclosure provides a method for vehicle positioning, the method comprising: acquiring point cloud information of a target area where the vehicle is located; determining the ground type of the target area based on the point cloud information; the ground type including horizontal ground or sloping ground; and determining the location information of the target vehicle based on the ground type and the point cloud information of the target area.

[0006] Optionally, determining the ground type of the target area based on the point cloud information includes: determining the angle between the plane containing the target area and a preset plane based on the point cloud information; and determining the ground type of the target area based on the angle.

[0007] Optionally, determining the ground type of the target area based on the included angle includes: determining the ground type as horizontal ground when the included angle is less than or equal to a preset angle threshold; or determining the ground type as sloping ground when the included angle is greater than the preset angle threshold.

[0008] Optionally, determining the location information of the target vehicle based on the ground type and the point cloud information of the target area includes: determining the predicted motion state of the vehicle based on the ground type; and determining the location information of the vehicle based on the predicted motion state and the point cloud information.

[0009] Optionally, determining the predicted motion state of the vehicle based on the ground type includes: when the ground type includes the horizontal ground, acquiring the yaw rate, lateral acceleration, and longitudinal acceleration of the vehicle, and determining the predicted motion state of the vehicle based on the yaw rate, lateral acceleration, and longitudinal acceleration; or, when the ground type includes the sloping ground, acquiring the pitch rate, roll rate, yaw rate, lateral acceleration, longitudinal acceleration, and vertical acceleration of the vehicle, and determining the predicted motion state of the vehicle based on the pitch rate, roll rate, yaw rate, lateral acceleration, longitudinal acceleration, and vertical acceleration.

[0010] Optionally, determining the vehicle's location information based on the predicted motion state and the point cloud information includes: updating the point cloud information based on the predicted motion state; and determining the vehicle's location information based on the updated point cloud information.

[0011] Optionally, determining the vehicle's location information based on the updated point cloud information includes: determining the vehicle's motion trajectory information based on the updated point cloud information; and determining the vehicle's location information based on the motion trajectory information and the predicted motion state.

[0012] Optionally, determining the vehicle's location information based on the motion trajectory information and the predicted motion state includes: determining a point cloud map corresponding to the area where the target region is located based on the motion trajectory information; and determining the vehicle's location information based on the vehicle's predicted motion state and the point cloud map.

[0013] Secondly, this disclosure provides a vehicle positioning device, the device comprising:

[0014] The acquisition module is used to acquire point cloud information of the target area where the vehicle is located;

[0015] A type determination module is used to determine the ground type of the target area based on the point cloud information; the ground type includes horizontal ground or sloping ground.

[0016] The location determination module is used to determine the location information of the target vehicle based on the ground type and the point cloud information of the target area.

[0017] Optionally, the type determination module is used to determine the angle between the plane where the target area is located and a preset plane based on the point cloud information; and to determine the ground type of the target area based on the angle.

[0018] Optionally, the type determination module is used to determine the ground type as horizontal ground when the included angle is less than or equal to a preset angle threshold; or, when the included angle is greater than the preset angle threshold, to determine the ground type as sloping ground.

[0019] Optionally, the location determination module is used to determine the predicted motion state of the vehicle based on the ground type; and to determine the location information of the vehicle based on the predicted motion state and the point cloud information.

[0020] Optionally, the position determination module is configured to, when the ground type includes the horizontal ground, acquire the yaw rate, lateral acceleration, and longitudinal acceleration of the vehicle, and determine the predicted motion state of the vehicle based on the yaw rate, lateral acceleration, and longitudinal acceleration; or, when the ground type includes the sloping ground, acquire the pitch rate, roll rate, yaw rate, lateral acceleration, longitudinal acceleration, and vertical acceleration of the vehicle, and determine the predicted motion state of the vehicle based on the pitch rate, roll rate, yaw rate, lateral acceleration, longitudinal acceleration, and vertical acceleration.

[0021] Optionally, the position determination module is used to update the point cloud information according to the predicted motion state; and to determine the position information of the vehicle according to the updated point cloud information.

[0022] Optionally, the position determination module is used to determine the vehicle's motion trajectory information based on the updated point cloud information; and to determine the vehicle's position information based on the motion trajectory information and the predicted motion state.

[0023] Optionally, the location determination module is used to determine the point cloud map corresponding to the area where the target area is located based on the motion trajectory information; and to determine the location information of the vehicle based on the predicted motion state of the vehicle and the point cloud map.

[0024] Thirdly, this disclosure provides a non-transitory computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, implement the steps in the above-described method.

[0025] Fourthly, this disclosure provides a vehicle positioning device, comprising: a memory storing a computer program thereon; and a processor for executing the computer program in the memory to implement the steps of the above method.

[0026] Fifthly, this disclosure provides a vehicle that includes the vehicle positioning device described above.

[0027] By employing the above technical solution, point cloud information of the target area where the vehicle is located is acquired; the ground type of the target area is determined based on the point cloud information; the ground type includes horizontal ground or sloping ground; and the position information of the target vehicle is determined based on the ground type and the point cloud information of the target area. In this way, by separately considering the vertical motion prediction of the vehicle on horizontal and sloping ground, vertical positioning drift of the vehicle is avoided, improving the accuracy of vehicle positioning across multiple levels in multi-level underground parking garages.

[0028] Other features and advantages of this disclosure will be described in detail in the following detailed description section. Attached Figure Description

[0029] The accompanying drawings are provided to further illustrate the present disclosure and form part of the specification. They are used together with the following detailed description to explain the present disclosure, but do not constitute a limitation thereof. In the drawings:

[0030] Figure 1 This application illustrates a method for vehicle positioning according to an exemplary embodiment.

[0031] Figure 2 This is a flowchart illustrating a method for determining ground type according to an exemplary embodiment of this application;

[0032] Figure 3 This is a block diagram of a vehicle positioning device according to an exemplary embodiment of the present disclosure;

[0033] Figure 4 This is a block diagram illustrating an electronic device according to an exemplary embodiment of the present disclosure;

[0034] Figure 5 This is a block diagram illustrating a vehicle according to an exemplary embodiment of the present disclosure. Detailed Implementation

[0035] The specific embodiments of this disclosure will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit this disclosure.

[0036] It should be noted that all actions involving the acquisition of signals, information, or data in this disclosure are carried out in compliance with the relevant data protection laws and policies of the country where the location is situated, and with authorization from the owner of the relevant device.

[0037] First, the application scenario of this disclosure is explained. This disclosure applies to the scenario of automatic parking of vehicles in underground garages. In this scenario, underground garages often cannot receive GNSS signals, have poor lighting conditions, and typically have multiple floors with narrow and complex roads. These characteristics increase the difficulty and complexity of positioning. For such underground garage scenarios, wheel speed sensors, IMUs, and other measurement sensors can be used to estimate the vehicle's state information at the next moment from a known location based on the continuous measurement of the vehicle's motion state by the sensors, thereby achieving vehicle positioning.

[0038] However, the aforementioned methods require high accuracy from the vehicle's wheel speedometer and IMU, which may not be met for some vehicles. Furthermore, the sensors themselves suffer from drift and cumulative errors. Therefore, related technologies typically employ point cloud matching between adjacent frames or extracting feature information from point clouds between adjacent frames to construct an optimization equation. Then, a nonlinear optimization method is used to solve the extremum problem, thereby achieving inter-frame pose transformation. Simultaneously, an incremental point cloud map is constructed, and the point cloud information from the latest scan frame is matched with the point cloud map to obtain the vehicle's pose information in the environment at the current moment. Additionally, loop closure detection technology can be used to compare the current frame with historical keyframes to reduce inter-frame cumulative errors and correct the point cloud map. However, the point cloud maps generated by this type of positioning scheme often exhibit significant vertical drift, resulting in insufficient vertical positioning accuracy and making it difficult to handle the positioning and recognition problems between different levels in multi-level underground parking garages.

[0039] To address the aforementioned technical problems, this disclosure provides a vehicle positioning method, storage medium, vehicle positioning device, and vehicle. The method includes: acquiring point cloud information of a target area where the vehicle is located; determining the ground type of the target area based on the point cloud information; the ground type including horizontal ground or sloping ground; and determining the position information of the target vehicle based on the ground type and the point cloud information of the target area. By separately considering the vertical motion prediction of the vehicle on horizontal and sloping ground, vertical positioning drift of the vehicle is avoided, improving the accuracy of vehicle positioning across multiple levels in multi-level underground parking garages.

[0040] The present disclosure will now be described in conjunction with specific embodiments.

[0041] Figure 1 This application illustrates a vehicle positioning method according to an exemplary embodiment, such as... Figure 1 As shown, the method includes:

[0042] S101. Obtain the point cloud information of the target area where the vehicle is located.

[0043] For example, when the vehicle is in motion, the original laser point cloud data can be obtained through the vehicle-mounted laser radar, and feature extraction can be performed on the original laser point cloud data to obtain point cloud information.

[0044] For example, the point cloud information could be the curvature of the point cloud output by the vehicle-mounted LiDAR in the current coordinate system. A certain number of points near a given point are selected to calculate the curvature of that point. Points with high curvature are designated as edge feature points, and points with low curvature are designated as planar feature points. A certain number of edge points with the highest curvature and planar points with the lowest curvature are selected for further processing. The formula for calculating curvature is shown below:

[0045]

[0046] Where X represents the spatial position of the laser point output by the vehicle radar, c is the local curvature of the feature point, S is the set of local points for calculating the curvature, i and j are any points in the set of local points, and L represents the coordinate system in which the laser point is located.

[0047] S102. Determine the ground type of the target area based on the point cloud information.

[0048] This ground type includes horizontal ground or sloping ground.

[0049] In some embodiments, the angle between the plane containing the target area and a preset plane is determined based on the point cloud information; the ground type of the target area is determined based on the angle.

[0050] For example, the preset plane can be a horizontal plane. The angle between the plane containing the target area and the horizontal plane is obtained. If the angle is less than or equal to a preset angle threshold, the ground type is determined to be a horizontal ground. Alternatively, if the angle is greater than the preset angle threshold, the ground type is determined to be a sloping ground.

[0051] In some other embodiments, the ground point cloud set of the plane where the target area is located can be determined based on the point cloud information, the normal vector of the plane where the target area is located can be obtained through the ground point cloud set, and the ground type of the target area can be determined based on the normal vector and the preset vertical unit vector.

[0052] For example, Figure 2 This is a flowchart illustrating a ground type determination method according to an exemplary embodiment of this application, which can be based on, as follows: Figure 2 The process shown determines the ground type of the target area:

[0053] S201. Obtain raw lidar point cloud data.

[0054] S202, Fitting ground point cloud information.

[0055] The RANSAC (Random Sample Consensus) algorithm is used to fit the ground point cloud information obtained from the original lidar point cloud data to determine the ground point cloud set.

[0056] S203. Transform the reference coordinate system.

[0057] Transform the reference coordinate system of the ground point cluster from the local coordinate system to the global coordinate system. Calculations performed using the global coordinate system will improve accuracy.

[0058] S204. Calculate the normal vector and the included angle.

[0059] The normal vector of the plane containing the target region in the global coordinate system can be obtained by using SVD (Singular Value Decomposition).

[0060] Suppose X = {(x k y k z k Let (x0, y0, z0) be the obtained ground point set, and (x0, y0, z0) be the average coordinates of the ground point cloud. Then, the model of the plane containing the target area can be represented as:

[0061] a(x k -x0)+b(y k -y0)+c(z k -z0)=0

[0062] Let N be the normal vector of the plane containing the target region. Expanding the above model, we get:

[0063]

[0064] AN=0

[0065] Decompose A=UΣV using the SVD method T In this matrix, U and V are two orthogonal matrices after SVD decomposition of matrix A. U is the left singular matrix and V is the right singular matrix. The third column of matrix V is the normal vector of the ground. Then, the angle between the normal vector and the vertical unit vector [0 0 1] of the global coordinate system is calculated.

[0066] S205. Determine the ground type based on the included angle.

[0067] The ground type is determined based on the included angle. For example, the preset angle threshold can be 2° or 3°. Taking the preset angle threshold of 2° as an example, if the included angle is less than or equal to 2°, the ground type is determined to be horizontal ground; if the included angle is greater than 2°, the ground type is determined to be sloping ground.

[0068] In this way, by fitting the ground point cloud information, the ground point cloud set of the target area is obtained, and the normal vector of the plane where the target area is located is determined based on the ground point cloud set. Then, the ground type of the target area is determined based on the normal vector and the vertical vector of the preset global coordinate system, which helps to improve the accuracy of determining the ground type.

[0069] S103. Determine the location information of the target vehicle based on the ground type and the point cloud information of the target area.

[0070] In some feasible approaches, the predicted motion state of the vehicle can be determined based on the ground type; the predicted motion state includes the vehicle's speed, acceleration, and position change information; and the vehicle's position information can be determined based on the predicted motion state and the point cloud information.

[0071] In some embodiments, the vehicle's motion parameters, including yaw rate, pitch rate, roll rate, lateral acceleration, longitudinal acceleration, and vertical acceleration, can be determined based on the ground type; and the predicted motion state of the vehicle can be determined based on these motion parameters.

[0072] For example, if the ground type includes the horizontal ground, the yaw rate, lateral acceleration, and longitudinal acceleration of the vehicle are obtained, and the predicted motion state of the vehicle is determined based on the yaw rate, lateral acceleration, and longitudinal acceleration; or, if the ground type includes the sloping ground, the pitch rate, roll rate, yaw rate, lateral acceleration, longitudinal acceleration, and vertical acceleration of the vehicle are obtained, and the predicted motion state of the vehicle is determined based on the pitch rate, roll rate, yaw rate, lateral acceleration, longitudinal acceleration, and vertical acceleration.

[0073] For example, if the ground type of the target area is level at the current moment, the pitch and roll angular velocities output by the IMU are set to zero, while the yaw angular velocities remain unchanged; if the ground is sloped at the current moment, the vehicle's driving parameters are determined based on the pitch, roll, and yaw angular velocities actually output by the IMU.

[0074] For horizontal ground conditions, the motion control variables are:

[0075] u=[ω T a T ] T

[0076] Where ω = [roll = 0 pitch = 0 yaw] is the angular velocity vector, and a is the acceleration vector.

[0077] For sloping ground conditions, the motion control parameters are:

[0078] u=[ω T a T ] T

[0079] In ω = [roll pitch yaw], roll, pitch, and yaw all take the actual output values ​​of the IMU.

[0080] In other embodiments, the vehicle's motion state can be predicted based on the selected actual IMU output value to obtain the predicted motion state of the vehicle. If the vehicle is currently on a horizontal surface, no state prediction is made for the vertical motion, thus avoiding the accumulation of errors in the vertical direction. If the vehicle is currently on a sloping surface, the vertical motion state of the vehicle is predicted based on the vehicle's pitch and roll angular velocities.

[0081] Among them, motion state prediction:

[0082]

[0083] Covariance prediction:

[0084]

[0085] In the formula, x is the vehicle's driving parameter, P is the state error covariance, f(·) is the state transition function, F is the state transition matrix, and Q is the noise matrix.

[0086] Furthermore, since the points in a single frame of point cloud are not collected simultaneously, the radar needs to move along with the vehicle during the acquisition process, resulting in different coordinate systems for different laser points. To improve the accuracy of the acquired laser points, the reference coordinate system of the point cloud information needs to be corrected to eliminate motion distortion caused by vehicle movement.

[0087] In some other embodiments, the point cloud information can be updated based on the predicted motion state; and the vehicle's location information can be determined based on the updated point cloud information.

[0088] For example, to compensate for motion distortion caused by the relative motion between the feature point scanning time and the end time of the current frame scanning, the motion information of the carrier predicted by the aforementioned IMU is used. The position of the lidar at the end time of the current frame scanning is obtained from the motion prediction module. Starting from the beginning, the feature points at the scan time are projected onto the end time of the frame, and motion compensation is performed on them:

[0089]

[0090] in, This represents the point cloud information of the vehicle at time j after removing motion distortion.

[0091] In this way, the point cloud information of the target area is updated according to the vehicle's motion state, removing the distortion features of the point cloud information and eliminating the errors in the point cloud information caused by the vehicle's motion, which helps to improve the accuracy of the point cloud information.

[0092] In addition, to improve the accuracy of predicting the vehicle's motion state, a Kalman filter can be applied to the predicted motion state to obtain the vehicle's preferred predicted motion state; based on the preferred predicted motion state and the point cloud information, the vehicle's position information can be determined.

[0093] For example, transform the feature points after removing motion distortion to the global coordinate system:

[0094]

[0095] In the formula, These are the coordinates of the feature point in the radar coordinate system at the end of the scan frame. I T L This is the transformation matrix from the radar coordinate system to the IMU coordinate system. This is the transformation matrix from the IMU coordinate system to the global coordinate system. These are the coordinates of the feature point in the global coordinate system.

[0096] Calculate the residual, which involves calculating the distance between the feature points of the scan frame transformed to the global coordinate system and the nearest neighbor feature points extracted from the map:

[0097]

[0098] In the formula, z j For the calculated residual results, G q j These are feature points on the map.

[0099] The calculated residuals are substituted into the update equation of the iterative Kalman filter to estimate the optimal motion state at the current time. The Kalman gain is calculated as follows:

[0100] K = PH T (HPH T +R) -1

[0101] In the formula, K is the Kalman gain, H is the observation matrix, P is the covariance matrix, and R is the noise matrix.

[0102] The state update and covariance update equations for the iterative Kalman filter are as follows:

[0103]

[0104]

[0105] In the formula, This is the optimal estimate of the vehicle's motion state in the current frame, i.e., the predicted motion state of the vehicle. Let z be the covariance matrix corresponding to the feature point, z be the feature point residual, which expresses the positional change between the feature point in the current frame and the corresponding feature point in the previous frame; I represents the identity matrix; J represents the Jacobian matrix.

[0106] It should be noted that, in the above embodiments, the point cloud information can also be updated based on the preferred predicted motion state; and the vehicle's position information can be determined based on the updated point cloud information. Specifically, motion distortion can be removed from the point cloud information based on the preferred predicted motion state. This process is the same as updating the point cloud information based on the predicted motion state, and will not be described again here to avoid repetition.

[0107] Thus, by applying Kalman filtering to the predicted motion state, the optimal predicted motion state of the vehicle can be obtained, which helps to improve the accuracy of the vehicle's trajectory.

[0108] In some other embodiments, the vehicle's motion trajectory information can be determined based on the updated point cloud information; and the vehicle's position information can be determined based on the motion trajectory information.

[0109] For example, the point cloud map corresponding to the area where the target area is located is determined based on the motion trajectory information; the location information of the vehicle is determined based on the vehicle's motion trajectory information and the point cloud map.

[0110] For example, point cloud information obtained during vehicle movement can be acquired, fitted to obtain a ground point cloud set, and then incrementally modified using point cloud information obtained during subsequent vehicle movement to determine the vehicle's trajectory information. Finally, motion distortion of the ground point cloud set is removed based on the vehicle's predicted motion state to obtain a point cloud map corresponding to the area containing the target region.

[0111] For example, the predicted motion state obtained above, or the preferred predicted motion state, can be projected onto the global coordinate system, and the point cloud information at the current moment can be registered into the point cloud map to generate the latest map and odometry information:

[0112]

[0113] In the formula, To add points to the map, This is the optimal estimate of the point in the radar coordinate system of the current frame.

[0114] Using the above method, point cloud information of the target area where the vehicle is located is obtained; the ground type of the target area is determined based on the point cloud information; the ground type includes horizontal ground or sloping ground; and the position information of the target vehicle is determined based on the ground type and the point cloud information of the target area. In this way, the vertical motion prediction of the vehicle on horizontal ground and sloping ground are considered separately, avoiding the drift of the vehicle's positioning information in the vertical direction, which is beneficial for achieving accurate positioning between floors in multi-level underground parking garages.

[0115] Figure 3 This disclosure illustrates a vehicle positioning device according to an exemplary embodiment, such as... Figure 3 As shown, the device includes:

[0116] The acquisition module 301 is used to acquire point cloud information of the target area where the vehicle is located;

[0117] The type determination module 302 is used to determine the ground type of the target area based on the point cloud information; the ground type includes horizontal ground or sloping ground.

[0118] The location determination module 303 is used to determine the location information of the target vehicle based on the ground type and the point cloud information of the target area.

[0119] Optionally, the type determination module 302 is used to determine the angle between the plane where the target area is located and the preset plane based on the point cloud information; and to determine the ground type of the target area based on the angle.

[0120] Optionally, the type determination module 302 is used to determine the ground type as horizontal ground when the included angle is less than or equal to a preset angle threshold; or to determine the ground type as sloping ground when the included angle is greater than the preset angle threshold.

[0121] Optionally, the location determination module 303 is used to determine the predicted motion state of the vehicle based on the ground type; and to determine the location information of the vehicle based on the predicted motion state and the point cloud information.

[0122] Optionally, the position determination module 303 is configured to, when the ground type includes the horizontal ground, acquire the yaw rate, lateral acceleration, and longitudinal acceleration of the vehicle, and determine the predicted motion state of the vehicle based on the yaw rate, lateral acceleration, and longitudinal acceleration; or, when the ground type includes the sloping ground, acquire the pitch rate, roll rate, yaw rate, lateral acceleration, longitudinal acceleration, and vertical acceleration of the vehicle, and determine the predicted motion state of the vehicle based on the pitch rate, roll rate, yaw rate, lateral acceleration, longitudinal acceleration, and vertical acceleration.

[0123] Optionally, the position determination module 303 is used to update the point cloud information based on the predicted motion state; and to determine the position information of the vehicle based on the updated point cloud information.

[0124] Optionally, the location determination module 303 is used to determine the vehicle's motion trajectory information based on the updated point cloud information; and to determine the vehicle's location information based on the motion trajectory information and the predicted motion state.

[0125] Optionally, the location determination module 303 is used to determine the point cloud map corresponding to the area where the target region is located based on the motion trajectory information; and to determine the vehicle's location information based on the vehicle's predicted motion state and the point cloud map.

[0126] The above technical solution involves acquiring point cloud information of the target area where the vehicle is located; determining the ground type of the target area based on the point cloud information; the ground type includes horizontal ground or sloping ground; and determining the position information of the target vehicle based on the ground type and the point cloud information of the target area. By separately considering the vertical motion prediction of the vehicle on horizontal and sloping ground, vertical positioning drift of the vehicle is avoided, improving the accuracy of vehicle positioning across multiple levels in multi-level underground parking garages.

[0127] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0128] Figure 4 This is a block diagram illustrating an electronic device 400 according to an exemplary embodiment. The electronic device may be a vehicle positioning device, such as... Figure 4 As shown, the electronic device 400 may include a processor 401 and a memory 402. The electronic device 400 may also include one or more of a multimedia component 403, an input / output (I / O) interface 404, and a communication component 405.

[0129] The processor 401 controls the overall operation of the electronic device 400 to complete all or part of the steps in the vehicle positioning method described above. The memory 402 stores various types of data to support the operation of the electronic device 400. This data may include, for example, instructions for any application or method operating on the electronic device 400, and application-related data such as contact data, sent and received messages, pictures, audio, video, etc. The memory 402 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. Multimedia component 403 may include a screen and an audio component. The screen may be, for example, a touchscreen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in memory 402 or transmitted via communication component 405. The audio component also includes at least one speaker for outputting audio signals. I / O interface 404 provides an interface between processor 401 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual or physical buttons. Communication component 405 is used for wired or wireless communication between the electronic device 400 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IoT, eMTC, or other 5G technologies, or combinations thereof, is not limited here. Therefore, the corresponding communication component 405 may include: a Wi-Fi module, a Bluetooth module, an NFC module, etc.

[0130] In an exemplary embodiment, the electronic device 400 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the vehicle positioning method described above.

[0131] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, which, when executed by a processor, implement the steps of the vehicle positioning method described above. For example, the computer-readable storage medium may be the memory 402 including the program instructions described above, which may be executed by the processor 401 of the electronic device 400 to complete the vehicle positioning method described above.

[0132] In another exemplary embodiment, a computer program product is also provided, comprising a computer program executable by a programmable device, the computer program having a code portion for performing the vehicle positioning method described above when executed by the programmable device.

[0133] Figure 5 This disclosure illustrates a vehicle 10 according to an exemplary embodiment, such as... Figure 5 As shown, the vehicle 10 includes the aforementioned electronic equipment 400.

[0134] The preferred embodiments of the present disclosure have been described in detail above with reference to the accompanying drawings. However, the present disclosure is not limited to the specific details of the above embodiments. Within the scope of the technical concept of the present disclosure, various simple modifications can be made to the technical solutions of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.

[0135] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, this disclosure will not describe the various possible combinations separately.

[0136] Furthermore, various different embodiments of this disclosure can be combined in any way, as long as they do not violate the spirit of this disclosure, they should also be regarded as the content disclosed in this disclosure.

Claims

1. A method for vehicle positioning, characterized in that, The method includes: Obtain point cloud information of the target area where the vehicle is located; The ground type of the target area is determined based on the point cloud information; the ground type includes horizontal ground or sloping ground. The location information of the vehicle is determined based on the ground type and the point cloud information of the target area; Determining the vehicle's location information based on the ground type and the point cloud information of the target area includes: Based on the ground type, determine the predicted motion state of the vehicle; The vehicle's position information is determined based on the predicted motion state and the point cloud information; Determining the predicted motion state of the vehicle based on the ground type includes: When the ground type includes the horizontal ground, the yaw rate, lateral acceleration, and longitudinal acceleration of the vehicle are obtained, and the predicted motion state of the vehicle is determined based on the yaw rate, lateral acceleration, and longitudinal acceleration; or, When the ground type includes the sloping ground, the pitch rate, roll rate, yaw rate, lateral acceleration, longitudinal acceleration, and vertical acceleration of the vehicle are obtained, and the predicted motion state of the vehicle is determined based on the pitch rate, roll rate, yaw rate, lateral acceleration, longitudinal acceleration, and vertical acceleration.

2. The method according to claim 1, characterized in that, Determining the ground type of the target area based on the point cloud information includes: Based on the point cloud information, determine the angle between the plane containing the target region and the preset plane; The ground type of the target area is determined based on the included angle.

3. The method according to claim 2, characterized in that, Determining the ground type of the target area based on the included angle includes: If the included angle is less than or equal to a preset angle threshold, the ground type is determined to be a horizontal ground; or, If the included angle is greater than a preset angle threshold, the ground type is determined to be a sloping ground.

4. The method according to claim 1, characterized in that, Determining the vehicle's position information based on the predicted motion state and the point cloud information includes: Update the point cloud information based on the predicted motion state; The location information of the vehicle is determined based on the updated point cloud information.

5. The method according to claim 4, characterized in that, Determining the vehicle's location information based on the updated point cloud information includes: Based on the updated point cloud information, the vehicle's motion trajectory information is determined; The vehicle's position information is determined based on the motion trajectory information and the predicted motion state.

6. The method according to claim 5, characterized in that, Determining the vehicle's position information based on the motion trajectory information and the predicted motion state includes: Based on the motion trajectory information, determine the point cloud map corresponding to the area where the target region is located; The vehicle's location information is determined based on the vehicle's predicted motion state and the point cloud map.

7. A non-transitory computer-readable storage medium having computer program instructions stored thereon, characterized in that, When executed by a processor, the program instructions implement the steps of the method described in any one of claims 1-6.

8. A vehicle positioning device, characterized in that, include: A memory on which computer programs are stored; A processor for executing the computer program in the memory to implement the steps of the method according to any one of claims 1-6.

9. A vehicle, characterized in that, The vehicle includes the vehicle positioning device as described in claim 8.

Images