Vehicle positioning method, apparatus, device, medium, and product

Abstract

The application discloses a vehicle positioning method, device, equipment, medium and product, and relates to the technical field of automatic driving. The vehicle positioning method comprises the following steps: acquiring a first label coordinate of an ultra-wideband label device on a target vehicle in a first coordinate system, the first coordinate system being a plane rectangular coordinate system constructed with a first ultra-wideband base station as an origin; converting the first label coordinate into a second coordinate system and determining a first pose matrix of the ultra-wideband label device in the second coordinate system, the second coordinate system being a world coordinate system with an inertial measurement unit as an origin; determining a sensor pose matrix matched with a target vehicle sensor according to the first pose matrix, the target vehicle sensor comprising at least one of a radar and a camera; and performing fusion positioning on the target vehicle based on the first pose matrix and the sensor pose matrix to obtain a vehicle positioning result of the target vehicle.

Description

Technical Field

[0001] This application belongs to the field of autonomous driving technology, and in particular relates to a vehicle positioning method, device, equipment, medium and product. Background Technology

[0002] Localization, environmental perception, planning, control, simulation, and infrastructure together constitute the six core modules of autonomous driving. They work together to ensure the safety and comfort of autonomous vehicles. Among them, the localization module is primarily responsible for answering the question "Where is the car now?" and is a core foundational module for autonomous driving.

[0003] In existing methods, the positioning of autonomous vehicles mainly adopts a fusion positioning scheme, which integrates onboard sensors such as Global Navigation Satellite System (GNSS), Inertial Measurement Unit (IMU) and LiDAR to achieve accurate positioning of autonomous vehicles.

[0004] However, in indoor scenarios such as tunnels, the lack of GNSS signals cannot provide initial pose for onboard sensors, resulting in poor positioning accuracy for autonomous vehicles. Summary of the Invention

[0005] This application provides a vehicle positioning method, device, equipment, medium, and product that can improve the positioning accuracy of autonomous vehicles.

[0006] One aspect of this application provides a vehicle positioning method, including:

[0007] Obtain the coordinates of the first tag of the ultra-wideband tag device on the target vehicle in the first coordinate system, where the first coordinate system is a plane rectangular coordinate system constructed with the first ultra-wideband base station as the origin;

[0008] Transform the coordinates of the first tag into the second coordinate system to determine the first pose matrix of the ultra-wideband tag device in the second coordinate system. The second coordinate system is the world coordinate system with the inertial measurement unit as the origin.

[0009] Based on the first pose matrix, determine the sensor pose matrix that matches the target vehicle sensor, which includes at least one of radar and camera.

[0010] Based on the first pose matrix and the sensor pose matrix, the target vehicle is fused and localized to obtain the vehicle localization result.

[0011] One aspect of this application provides a vehicle positioning device, including:

[0012] The coordinate acquisition module is used to acquire the first tag coordinates of the ultra-wideband tag device on the target vehicle in the first coordinate system, which is a plane rectangular coordinate system constructed with the first ultra-wideband base station as the origin.

[0013] The pose determination module is used to transform the coordinates of the first tag to the second coordinate system and determine the first pose matrix of the ultra-wideband tag device in the second coordinate system. The second coordinate system is the world coordinate system with the inertial measurement unit as the origin.

[0014] The pose determination module is also used to determine a sensor pose matrix that matches the target vehicle sensor based on the first pose matrix. The target vehicle sensor includes at least one of radar and camera.

[0015] The vehicle localization module is used to perform fusion localization of the target vehicle based on the first pose matrix and the sensor pose matrix to obtain the vehicle localization result.

[0016] In one aspect of this application, an electronic device is provided, the device including: a memory and a program or instructions stored in the memory and executable on a processor, wherein when the program or instructions are executed by the processor, they implement the vehicle positioning method provided in any aspect of the above-described embodiments of this application.

[0017] In one aspect of the embodiments of this application, a readable storage medium is provided, on which a program or instructions are stored, which, when executed by a processor, implement the vehicle positioning method provided in any aspect of the embodiments of this application described above.

[0018] In one aspect of the embodiments of this application, a computer program product is provided, wherein when the instructions in the computer program product are executed by the processor of an electronic device, the electronic device performs the vehicle positioning method provided in any aspect of the embodiments of this application described above.

[0019] In the vehicle positioning method provided in this application embodiment, the first tag coordinates of the ultra-wideband tag device on the target vehicle in the first coordinate system are first obtained. These first tag coordinates are then transformed to the second coordinate system to determine the first pose matrix of the ultra-wideband tag device in the second coordinate system. Next, based on the first pose matrix, a sensor pose matrix matching the target vehicle-mounted sensor is determined. Finally, based on the first pose matrix and the sensor pose matrix, the target vehicle is fused for positioning to obtain the vehicle positioning result. Thus, this application embodiment uses an ultra-wideband tag device to provide an initial pose for the target vehicle-mounted sensor, thereby accurately determining the sensor pose matrix matching the target vehicle-mounted sensor. Furthermore, accurate fusion positioning of the target vehicle can be performed based on the first pose matrix and the sensor pose matrix. This avoids the problem of not being able to provide an initial pose for the target vehicle-mounted sensor due to the lack of GNSS signals, thereby improving the positioning accuracy of autonomous vehicles. Attached Figure Description

[0020] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a schematic flowchart of a vehicle positioning method provided in one embodiment of this application;

[0022] Figure 2 This is a schematic diagram of the layout of an ultra-wideband base station provided in one embodiment of this application;

[0023] Figure 3 This is a schematic diagram of coordinate calculation for an ultra-wideband tag device provided in one embodiment of this application;

[0024] Figure 4 This is a schematic diagram of the structure of a vehicle positioning device provided in one embodiment of this application;

[0025] Figure 5 This is a schematic diagram of the structure of a vehicle positioning device provided in one embodiment of this application. Detailed Implementation

[0026] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.

[0027] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0028] It should be noted that the acquisition, storage, use, and processing of data in the technical solution of this application all comply with the relevant provisions of national laws and regulations.

[0029] It should be noted that in the embodiments of this application, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of this application. However, it does not mean that the applicant has used or necessarily used the solution.

[0030] In existing methods, the localization of autonomous vehicles mainly adopts a fusion positioning scheme, which integrates onboard sensors such as the Global Navigation Satellite System (GNSS), Inertial Measurement Unit (INS), and LiDAR to achieve accurate positioning of autonomous vehicles. However, in indoor scenarios such as tunnels, the lack of GNSS signals cannot provide the onboard sensors with initial pose, resulting in poor positioning accuracy for autonomous vehicles.

[0031] The purpose of this application is to provide a vehicle positioning method, apparatus, device, medium, and product. The vehicle positioning method provided in this application first obtains the first tag coordinates of an ultra-wideband tag device on the target vehicle in a first coordinate system, transforms the first tag coordinates to a second coordinate system, and determines the first pose matrix of the ultra-wideband tag device in the second coordinate system. Then, based on the first pose matrix, a sensor pose matrix matching the target vehicle-mounted sensor is determined. Finally, based on the first pose matrix and the sensor pose matrix, the target vehicle is fused for positioning to obtain the vehicle positioning result. Thus, this application uses an ultra-wideband tag device to provide an initial pose for the target vehicle-mounted sensor, thereby accurately determining the sensor pose matrix matching the target vehicle-mounted sensor. Furthermore, accurate fusion positioning of the target vehicle can be performed based on the first pose matrix and the sensor pose matrix. This avoids the problem of not being able to provide an initial pose for the target vehicle-mounted sensor due to the lack of GNSS signals, thereby improving the positioning accuracy of autonomous vehicles.

[0032] The following describes specific embodiments of the vehicle positioning method, device, equipment, medium, and product provided in this application. The vehicle positioning method will be described first.

[0033] Figure 1 A flowchart of a vehicle positioning method is provided. This vehicle positioning method can be applied to a server and may include the following steps S101 to S104.

[0034] S101, Obtain the first tag coordinates of the ultra-wideband tag device on the target vehicle in the first coordinate system, where the first coordinate system is a plane rectangular coordinate system constructed with the first ultra-wideband base station as the origin.

[0035] In this embodiment, the Ultra-Wideband (UWB) tag device is a device that uses ultra-wideband technology for precise positioning.

[0036] An ultra-wideband (UWB) base station is a base station device used in ultra-wideband communication systems. It is responsible for transmitting and receiving UWB signals, communicating with UWB tag devices or other UWB base stations, and realizing data transmission and location functions.

[0037] The first coordinate system is a Cartesian coordinate system constructed with any ultra-wideband base station in the target area where the target vehicle is located as the origin. The first tag coordinate is the coordinate position of the ultra-wideband tag device in the first coordinate system.

[0038] As an example, the server deploys at least one ultra-wideband (UWB) base station in the target area where the target vehicle is located, and then selects one UWB base station as the origin to construct a first coordinate system. Simultaneously, one or more UWB tag devices are installed on the target vehicle.

[0039] Then, through communication between the first ultra-wideband base station and the ultra-wideband tag device, the position of the ultra-wideband tag device relative to the first ultra-wideband base station, i.e., the coordinates of the first tag, is calculated using algorithms such as time difference ranging or time of flight.

[0040] S102, transform the coordinates of the first tag to the second coordinate system, and determine the first pose matrix of the ultra-wideband tag device in the second coordinate system. The second coordinate system is the world coordinate system with the inertial measurement unit as the origin.

[0041] In this embodiment, an inertial measurement unit is a device that measures and reports a specific force and angular velocity of an object, and in some cases, the orientation of the object around a magnetic field.

[0042] The second coordinate system is a world coordinate system constructed with the inertial measurement unit on the target vehicle as the origin.

[0043] The first pose matrix is ​​used to describe the position and orientation of the ultra-wideband tag device in the second coordinate system.

[0044] As an example, the server, based on a preset transformation relationship (e.g., translation and rotation matrices), and combining the relative positional relationship between the first ultra-wideband base station and the inertial measurement unit, as well as the current attitude of the target vehicle, transforms the coordinates of the first label from the first coordinate system to the second coordinate system. Then, the transformed label coordinates and their associated attitude information (e.g., rotation angle) are combined into a pose matrix, namely the first pose matrix.

[0045] S103, Based on the first pose matrix, determine the sensor pose matrix that matches the target vehicle sensor, the target vehicle sensor including at least one of radar and camera.

[0046] In this embodiment, the sensor pose matrix is ​​used to describe the position and orientation of the target vehicle sensor in the second coordinate system.

[0047] As an example, the server first obtains the installation position and attitude relationship of the target vehicle sensor relative to the inertial measurement unit. Then, using the first pose matrix to give the initial pose of the target vehicle sensor, and based on the installation position and attitude relationship of the target vehicle sensor relative to the inertial measurement unit, it calculates the sensor pose matrix that matches the target vehicle sensor.

[0048] S104. Based on the first pose matrix and the sensor pose matrix, the target vehicle is fused and located to obtain the vehicle localization result.

[0049] In this embodiment, the server fuses the precise location information provided by ultra-wideband technology, the real-time attitude information provided by the IMU, and environmental perception information from sensors such as radar and cameras, based on the first pose matrix and the sensor pose matrix. Specifically, this fusion can be achieved using algorithms such as Kalman filtering and particle filtering.

[0050] Finally, through data fusion processing, the precise position and attitude of the target vehicle at the current moment are calculated, which is the vehicle positioning result.

[0051] In the vehicle localization method provided in this embodiment, the first tag coordinates of the ultra-wideband tag device on the target vehicle in the first coordinate system are first obtained. These first tag coordinates are then transformed to the second coordinate system to determine the first pose matrix of the ultra-wideband tag device in the second coordinate system. Next, based on the first pose matrix, a sensor pose matrix matching the target vehicle sensor is determined. Finally, based on the first pose matrix and the sensor pose matrix, the target vehicle is fused for localization to obtain the vehicle localization result. Thus, this embodiment uses an ultra-wideband tag device to provide an initial pose for the target vehicle sensor, thereby accurately determining the sensor pose matrix matching the target vehicle sensor. Furthermore, accurate fusion localization of the target vehicle can be achieved based on the first pose matrix and the sensor pose matrix. This avoids the problem of not being able to provide an initial pose for the target vehicle sensor due to the lack of GNSS signals, thereby improving the localization accuracy of autonomous vehicles.

[0052] As an optional embodiment, S101 may specifically include:

[0053] Obtain the distance between the ultra-wideband tag device and each ultra-wideband base station;

[0054] The N ultra-wideband base stations with the smallest interval distance are determined as the second ultra-wideband base station, where N is a positive integer not less than 3;

[0055] Based on the first base station coordinates of each second ultra-wideband base station in the first coordinate system, and the interval distance between each second ultra-wideband base station and the ultra-wideband tag device, the first tag coordinates of the ultra-wideband tag device in the first coordinate system are determined.

[0056] In this embodiment, the second ultra-wideband base station is one of the N ultra-wideband base stations with the smallest interval distance to the ultra-wideband tag device, and is used to calculate the first tag coordinates of the ultra-wideband tag device in the first coordinate system.

[0057] As an example, such as Figure 2The diagram shows a layout schematic of an ultra-wideband base station. It employs eight ultra-wideband base stations, named A0 to A7, arranged at a distance d between them, forming a rectangular layout.

[0058] Simultaneously, an ultra-wideband tag device T0 and a T1 are respectively installed on the left and right sides of the target vehicle. The distance between the ultra-wideband tag device and the ultra-wideband base station is named r. For example, Figure 2 In this diagram, r2 represents the distance between ultra-wideband base station A2 and ultra-wideband tag device T0, r3 represents the distance between ultra-wideband base station A3 and ultra-wideband tag device T1, r6 represents the distance between ultra-wideband base station A6 and ultra-wideband tag device T0, and r7 represents the distance between ultra-wideband base station A7 and ultra-wideband tag device T1.

[0059] For each ultra-wideband tag device, the following steps can be used to determine the coordinates of the first tag in the first coordinate system:

[0060] First, the server constructs a coordinate system between planes using any one of the ultra-wideband base stations as the origin, thus obtaining the first coordinate system. Simultaneously, it obtains the first base station coordinates of each ultra-wideband base station within the first coordinate system.

[0061] Then, using UWB technology, the UWB tag device sends signals to all UWB base stations. Upon receiving the signals, the UWB base stations record timestamps and return this information to the server. The server can then calculate the distance between the UWB tag device and each UWB base station by measuring the round-trip time (RTT) or time difference of arrival (TDOA).

[0062] Then, the distances between the UWB tag device and each UWB base station are sorted in ascending order, and the three UWB base stations with the smallest distances are selected as the second UWB base stations. Finally, based on the first base station coordinates of each second UWB base station in the first coordinate system and the distances between each second UWB base station and the UWB tag device, the first tag coordinates of the UWB tag device in the first coordinate system are calculated.

[0063] Specifically, such as Figure 3 The diagram illustrates the coordinate calculation of an ultra-wideband (UWB) tag device. Assume the three selected second UWB base stations are UWB base station A1, UWB base station A2, and UWB base station A3. The distance between UWB base station A1 and the UWB tag device is denoted as r1, the distance between UWB base station A2 and the UWB tag device is denoted as r2, and the distance between UWB base station A3 and the UWB tag device is denoted as r3.

[0064] Thus, we can obtain the following formula 1:

[0065]

[0066] Among them, the first base station coordinates of ultra-wideband base station A1 in the first coordinate system are (x1, y1), the first base station coordinates of ultra-wideband base station A2 in the first coordinate system are (x2, y2), the first base station coordinates of ultra-wideband base station A3 in the first coordinate system are (x3, y3), and the first tag coordinates of ultra-wideband tag device in the first coordinate system are (x, y).

[0067] Subtracting each other from the equation in Formula 1 and simplifying, we get Formula 2:

[0068]

[0069] Solving Formula 2 above yields the coordinates of the first tag of the ultra-wideband tag device in the first coordinate system, as shown in Formula 3 below:

[0070]

[0071] in,

[0072] In this embodiment, the three UWB base stations closest to the UWB tag device are selected as the second UWB base stations. Therefore, based on the first base station coordinates of each second UWB base station in the first coordinate system, the first tag coordinates of the UWB tag device in the first coordinate system can be accurately calculated. Thus, selecting the three second UWB base stations with the strongest signal and least interference to calculate the first tag coordinates of the UWB tag device improves the accuracy of the first tag coordinate calculation.

[0073] As an optional embodiment, S102 may specifically include:

[0074] Transform the first tag coordinates to the standard world coordinate system to determine the second pose matrix of the ultra-wideband tag device in the standard world coordinate system;

[0075] Based on the extrinsic parameter matrix from the inertial measurement unit to the ultra-wideband tag device, the second pose matrix is ​​transformed to obtain the first pose matrix of the ultra-wideband tag device in the second coordinate system.

[0076] In this embodiment, the standard world coordinate system is used to represent the pre-defined default world coordinate system. Specifically, the Universal Transverse Mercator Grid System (UTM) coordinate system can be used as the world coordinate system.

[0077] The extrinsic parameter matrix is ​​used to characterize the positional relationship between the inertial measurement unit and the ultra-wideband tag device.

[0078] As an example, the server first transforms the coordinates of the first tag device in the first coordinate system to the standard world coordinate system using a coordinate transformation matrix that describes the relationship between the first coordinate system and the standard world coordinate system. Simultaneously, based on the coordinates and orientation of the ultra-wideband tag device in the standard world coordinate system, a matrix describing its pose, namely the second pose matrix, can be constructed.

[0079] Then, after transposing the extrinsic parameter matrix from the inertial measurement unit to the ultra-wideband tag device, multiplying it by the second pose matrix, the first pose matrix of the ultra-wideband tag device in the second coordinate system can be obtained.

[0080] In this embodiment, the coordinates of the first tag are transformed into the second coordinate system, thereby accurately determining the first pose matrix of the ultra-wideband tag device in the second coordinate system. This helps to provide the initial pose of the target vehicle sensor using the first pose matrix, thus improving the positioning accuracy of autonomous vehicles.

[0081] As an optional embodiment, the first tag coordinates are transformed to the standard world coordinate system to determine the second pose matrix of the ultra-wideband tag device in the standard world coordinate system, which may specifically include:

[0082] Based on the first base station coordinates of each ultra-wideband base station in the first coordinate system and the second base station coordinates of each ultra-wideband base station in the standard world coordinate system, determine the transformation matrix from the first coordinate system to the standard world coordinate system.

[0083] Based on the transformation matrix, the coordinates of the first label are converted into the coordinates of the second label in the standard world coordinate system;

[0084] Based on the coordinates of the second tag, determine the yaw angle matrix of the ultra-wideband tag device in the standard world coordinate system;

[0085] Based on the second tag coordinates and the yaw angle matrix, the second pose matrix of the ultra-wideband tag device in the standard world coordinate system is constructed.

[0086] In this embodiment, the yaw angle matrix is ​​used to characterize the rotation matrix calculated based on the yaw angle of the ultra-wideband tag device.

[0087] As an example, the server first collects the coordinates of each UWB base station in the first coordinate system and the coordinates of each UWB base station in the standard world coordinate system. Then, based on the first base station coordinates and the corresponding second base station coordinates, it solves for the transformation matrix from the first coordinate system to the standard world coordinate system using the least squares method, singular value decomposition, or other optimization methods.

[0088] Then, multiplying the first tag coordinates by the transformation matrix yields the second tag coordinates of the ultra-wideband tag device in the standard world coordinate system. Specifically, as shown in Formula 4 below:

[0089]

[0090] in, The second tag coordinates used to characterize the ultra-wideband tag device T0 in the standard world coordinate system of UTM. The second tag coordinates used to characterize the ultra-wideband tag device T1 in the standard world coordinate system of UTM. The transformation matrix used to characterize the transformation from the first coordinate system of UWB to the standard world coordinate system of UTM. The first tag coordinates used to characterize the ultra-wideband tag device T0 in the first coordinate system of UWB. The first tag coordinates of the ultra-wideband tag device T1 in the first coordinate system of UWB are used to characterize the first tag coordinates.

[0091] Then, based on the second tag coordinates of the ultra-wideband tag device in the standard world coordinate system, the yaw angle of the ultra-wideband tag device is calculated, thus forming the yaw angle matrix of the ultra-wideband tag device in the standard world coordinate system.

[0092] Finally, based on the second tag coordinates and the yaw angle matrix, the second pose matrix of the ultra-wideband tag device in the standard world coordinate system is constructed. Specifically, it is shown in the following formula 5:

[0093]

[0094] in, The second pose matrix used to characterize the ultra-wideband tag device T0 in the standard world coordinate system of the UTM. The second pose matrix used to characterize the ultra-wideband tag device T1 in the standard world coordinate system of the UTM. The yaw angle matrix used to characterize ultra-wideband tag devices in the standard world coordinate system of UTM. The second tag coordinates used to characterize the ultra-wideband tag device T0 in the standard world coordinate system of UTM. The second tag coordinates used to characterize the ultra-wideband tag device T1 in the standard world coordinate system of UTM.

[0095] This embodiment transforms the coordinates of the first tag into a standard world coordinate system, determining the second pose matrix of the ultra-wideband tag device in the standard world coordinate system. This facilitates the subsequent determination of the first pose matrix of the ultra-wideband tag device in the second coordinate system based on the second pose matrix. Furthermore, this first pose matrix helps provide the target vehicle-mounted sensor with an initial pose, thereby improving the positioning accuracy of autonomous vehicles.

[0096] As an optional embodiment, the transformation matrix from the first coordinate system to the standard world coordinate system is determined based on the first base station coordinates of each ultra-wideband base station in the first coordinate system and the second base station coordinates of each ultra-wideband base station in the standard world coordinate system. Specifically, this may include:

[0097] Based on the coordinates of each first base station and each second base station, determine the rotation matrix from the first coordinate system to the standard world coordinate system;

[0098] Based on the target second base station coordinates and the rotation matrix, a transformation matrix is ​​constructed from the first coordinate system to the standard world coordinate system. The target second base station coordinates are the second base station coordinates of the first ultra-wideband base station in the standard world coordinate system.

[0099] In this embodiment, the transformation matrix is ​​composed of a rotation matrix and a translation amount.

[0100] In this embodiment, the server first calculates the yaw, pitch, and roll angles of the target vehicle sequentially. Since the target vehicle is traveling on the ground, both pitch and roll are 0. In this case, the server only needs to perform rotation matching based on the coordinates of each first base station and the corresponding coordinates of each second base station to obtain the yaw angle of the target vehicle. Then, the rotation matrix from the first coordinate system to the standard world coordinate system is calculated according to the following formula 6:

[0101]

[0102] in, R is the rotation matrix used to characterize the rotation from the first coordinate system of UWB to the standard world coordinate system of UTM. x (rol)l is used to characterize the rotation matrix corresponding to the roll angle of the target vehicle, R x (pitch) is used to characterize the rotation matrix corresponding to the pitch angle of the target vehicle, R x (yaw) is used to characterize the rotation matrix corresponding to the yaw angle of the target vehicle.

[0103] Furthermore, the translation from the first coordinate system to the standard world coordinate system is the coordinate of the second base station in the standard world coordinate system for the first ultra-wideband base station. Finally, based on the rotation matrix and the translation, the transformation matrix from the first coordinate system to the standard world coordinate system can be determined using the following formula 7:

[0104]

[0105] in, The transformation matrix used to characterize the transformation from the first coordinate system of UWB to the standard world coordinate system of UTM. A rotation matrix used to characterize the rotation from the first coordinate system of UWB to the standard world coordinate system of UTM. Used to characterize the translation from the first coordinate system of UWB to the standard world coordinate system of UTM. The coordinates of the second base station are used to characterize the first ultra-wideband base station A0 in the standard world coordinate system of UTM.

[0106] In this embodiment, a transformation matrix from the first coordinate system to the standard world coordinate system is determined based on the first base station coordinates of each ultra-wideband (UWB) base station in the first coordinate system and the second base station coordinates of each UWB base station in the standard world coordinate system. This helps to accurately determine the first pose matrix of the UWB tag device in the second coordinate system based on the transformation matrix from the first coordinate system to the standard world coordinate system. Furthermore, this first pose matrix helps to provide the initial pose of the target vehicle-mounted sensor, thereby improving the positioning accuracy of autonomous vehicles.

[0107] As an optional embodiment, the ultra-wideband tag device includes a first ultra-wideband tag device and a second ultra-wideband tag device located symmetrically on both sides of the target vehicle, and the second tag coordinates include the first sub-tag coordinates of the first ultra-wideband tag device and the second sub-tag coordinates of the second ultra-wideband tag device;

[0108] Based on the second tag coordinates, determine the yaw angle matrix of the ultra-wideband tag device in the standard world coordinate system, which may specifically include:

[0109] Based on the coordinates of the first sub-label and the second sub-label, determine the difference in the horizontal and vertical coordinates between the coordinates of the first sub-label and the second sub-label.

[0110] Divide the difference in the vertical coordinate by the difference in the horizontal coordinate to obtain the yaw angle of the ultra-wideband tag device in the standard world coordinate system.

[0111] A matrix transformation is performed on the yaw angle to obtain the yaw angle matrix of the ultra-wideband tag device in the standard world coordinate system.

[0112] In this embodiment, as Figure 2As shown, a first ultra-wideband tag device T0 and a second ultra-wideband tag device T1 are respectively installed on both sides of the target vehicle, and the first ultra-wideband tag device T0 and the second ultra-wideband tag device T1 are symmetrical.

[0113] Then, the differences in the x-coordinate and y-coordinate of the coordinates of the first sub-tag of the first ultra-wideband tag device T0 and the second sub-tag of the second ultra-wideband tag device T1 are calculated. The difference in the y-coordinate is then divided by the difference in the x-coordinate to obtain the yaw angle of the ultra-wideband tag device in the standard world coordinate system.

[0114] Finally, the rotation matrix is ​​calculated using the yaw angle of the ultra-wideband tag device in the standard world coordinate system, thus obtaining the yaw angle matrix of the ultra-wideband tag device in the standard world coordinate system.

[0115] This embodiment accurately calculates the yaw angle matrix of the ultra-wideband tag device in the standard world coordinate system based on the second tag coordinates. This helps in subsequently determining the second pose matrix of the ultra-wideband tag device in the standard world coordinate system based on the yaw angle matrix, thereby improving the positioning accuracy of autonomous vehicles.

[0116] As an optional embodiment, the second pose matrix is ​​transformed based on the extrinsic parameter matrix from the inertial measurement unit to the ultra-wideband tag device to obtain the first pose matrix of the ultra-wideband tag device in the second coordinate system. Specifically, this may include:

[0117] Obtain the extrinsic parameter matrix from the inertial measurement unit to the ultra-wideband tag device;

[0118] Transpose the extrinsic matrix to obtain the transposed extrinsic matrix;

[0119] Multiplying the transposed extrinsic parameter matrix with the second pose matrix yields the first pose matrix of the ultra-wideband tag device in the second coordinate system.

[0120] In this embodiment, the server first obtains the extrinsic parameter matrix from the inertial measurement unit to the ultra-wideband tag device. The rotation matrix of this extrinsic parameter is an identity matrix, and the translation amount can be directly obtained through measurement.

[0121] Then, the extrinsic parameter matrix is ​​transposed to obtain the transposed extrinsic parameter matrix. Multiplying the transposed extrinsic parameter matrix by the second pose matrix yields the first pose matrix of the ultra-wideband tag device in the second coordinate system.

[0122] Specifically, the first pose matrix of the ultra-wideband tag device in the second coordinate system can be determined by the following formula 8:

[0123]

[0124] in, The first pose matrix used to characterize the ultra-wideband tag device T0 in the standard world coordinate system of the UTM centered on the IMU, i.e., the second coordinate system. The second position matrix used to characterize the ultra-wideband tag device T0 in the standard world coordinate system of the UTM. The extrinsic parameter matrix used to characterize the IMU to ultra-wideband tag device, and T used to characterize the transpose operation.

[0125] In this embodiment, by transforming the second pose matrix based on the extrinsic parameter matrix from the inertial measurement unit to the ultra-wideband tag device, the first pose matrix of the ultra-wideband tag device in the second coordinate system can be obtained. This helps to provide the initial pose of the target vehicle-mounted sensor using the first pose matrix, thereby improving the positioning accuracy of autonomous vehicles.

[0126] As an optional embodiment, S103 may specifically include:

[0127] Acquire map reference point cloud and first source point cloud, the first source point cloud being the point cloud collected in real time by the target vehicle's onboard sensors;

[0128] The map reference point cloud is divided into multiple grid spaces, and the point cloud mean and point cloud covariance in each grid space are obtained.

[0129] Based on the first pose matrix, the first source point cloud is transformed to obtain the second source point cloud;

[0130] Project the second source point cloud onto the corresponding grid space to obtain the joint probability density of the second source point cloud in the map reference point cloud;

[0131] Based on the joint probability density, the first pose matrix is ​​iteratively optimized until a preset stopping condition is met, thus obtaining a sensor pose matrix that matches the target vehicle sensor.

[0132] In this embodiment, the map reference point cloud is used to represent the pre-constructed high-precision map point cloud data, representing the static characteristics of the environment.

[0133] The first source point cloud is the point cloud data collected in real time by vehicle-mounted sensors (such as lidar, cameras, etc.), representing the dynamic observation of the current environment.

[0134] As an example, the server divides the map reference point cloud into multiple small 3D raster spaces. The size of each raster space can be adjusted according to actual needs to balance computational efficiency and accuracy. Then, for each raster space, the mean (representing the center location of the raster space) and covariance (describing the distribution characteristics of the point cloud within that raster space) of all points are calculated.

[0135] Then, using the first pose matrix as the initial pose, the first source point cloud is transformed from the sensor coordinate system to the global map coordinate system to obtain the second source point cloud. Each point in the transformed second source point cloud is then projected onto its corresponding grid space.

[0136] For each grid space, the joint probability density is calculated using the mean and covariance of points in the second source point cloud and the point cloud within the grid space. Specifically, Mahalanobis distance or a Gaussian distribution probability density function can be used to evaluate the degree of matching between the second source point cloud and the map reference point cloud within that grid.

[0137] Then, based on the joint probability density, optimization algorithms (such as Iterative Closest Point (ICP), Gauss-Newton method, Levenberg-Marquardt algorithm, etc.) are used to iteratively adjust the first pose matrix to maximize the matching degree between the second source point cloud and the map reference point cloud. The iterative process will continue until a preset stopping condition is met, such as the number of iterations reaching the upper limit, the pose change being less than a threshold, or the increase in joint probability density no longer being significant.

[0138] Finally, when the iteration stops, the final optimized sensor pose matrix is ​​obtained, which accurately reflects the position and orientation of the vehicle sensor in the current environment.

[0139] In this embodiment, the first pose matrix provides the initial pose for the target vehicle sensor, thereby enabling the accurate determination of the sensor pose matrix that matches the target vehicle sensor. Furthermore, fusing the first pose matrix with the sensor pose matrix for localization improves the positioning accuracy of autonomous vehicles.

[0140] As an optional embodiment, S104 may specifically include:

[0141] The acceleration and angular velocity measured by the inertial measurement unit are integrated to obtain the predicted pose of the target vehicle.

[0142] Using the first pose matrix and the sensor pose matrix as the observed pose, the predicted pose is corrected to obtain the vehicle localization result of the target vehicle.

[0143] In this embodiment, an inertial measurement unit (IMU) is a device capable of measuring the acceleration and angular velocity of an object, typically composed of an accelerometer and a gyroscope. In a vehicle positioning system, the IMU is installed on the vehicle to collect the vehicle's acceleration and angular velocity data in real time.

[0144] As an example, the server integrates the acceleration and angular velocity measured by the inertial measurement unit to obtain the vehicle's velocity and position information, as well as its attitude information (such as pitch, yaw, roll, etc.). Specifically, acceleration data can be integrated once to obtain velocity data, and then integrated again to obtain position data; angular velocity data can be integrated to obtain the change in attitude angle, and thus the current attitude angle.

[0145] Then, based on the velocity, position, and attitude information obtained from the integration operation, the predicted pose of the target vehicle can be generated. The predicted pose typically includes the vehicle's position coordinates, velocity vector, and attitude angles. The first pose matrix and the sensor pose matrix are used as the observed pose and fused with the predicted pose. Specifically, data fusion algorithms such as Kalman filtering and particle filtering can be used. These algorithms can comprehensively consider the errors of the predicted pose and the observed pose, as well as the correlation between them, thereby obtaining a more accurate vehicle localization result.

[0146] Then, based on the fused pose data, state correction is performed on the predicted pose. The correction process may include adjusting parameters such as the vehicle's position coordinates, velocity vector, and attitude angles to make the predicted pose closer to the true value.

[0147] Finally, after state correction, the final vehicle positioning result can be obtained. This vehicle positioning result typically includes parameters such as the vehicle's position coordinates, velocity vector, and attitude angles, and can be used for applications such as vehicle navigation, path planning, and autonomous driving.

[0148] In this embodiment, the target vehicle is located by fusion based on the first pose matrix and the sensor pose matrix, resulting in the vehicle's localization. Thus, by employing a fusion localization method, the localization accuracy of autonomous vehicles can be improved.

[0149] Based on vehicle positioning methods, this application also provides specific embodiments of vehicle positioning devices.

[0150] like Figure 4 As shown, the vehicle positioning device 400 provided in this application embodiment includes a coordinate acquisition module 410, a pose determination module 420, and a vehicle positioning module 430.

[0151] The coordinate acquisition module 410 is used to acquire the first tag coordinates of the ultra-wideband tag device on the target vehicle in the first coordinate system, wherein the first coordinate system is a plane rectangular coordinate system constructed with the first ultra-wideband base station as the origin;

[0152] The pose determination module 420 is used to transform the coordinates of the first tag to the second coordinate system and determine the first pose matrix of the ultra-wideband tag device in the second coordinate system. The second coordinate system is the world coordinate system with the inertial measurement unit as the origin.

[0153] The pose determination module 420 is also used to determine a sensor pose matrix that matches the target vehicle sensor based on the first pose matrix. The target vehicle sensor includes at least one of radar and camera.

[0154] The vehicle positioning module 430 is used to perform fusion positioning of the target vehicle based on the first pose matrix and the sensor pose matrix to obtain the vehicle positioning result of the target vehicle.

[0155] As an optional embodiment, the coordinate acquisition module 410 may specifically include the following units:

[0156] The distance acquisition unit is used to acquire the interval distance between the ultra-wideband tag device and each ultra-wideband base station;

[0157] The base station determination unit is used to determine the first N ultra-wideband base stations with the smallest interval distance as the second ultra-wideband base station, where N is a positive integer not less than 3;

[0158] The coordinate determination unit is used to determine the first tag coordinates of the ultra-wideband tag device in the first coordinate system based on the first base station coordinates of each second ultra-wideband base station in the first coordinate system and the interval distance between each second ultra-wideband base station and the ultra-wideband tag device.

[0159] As an optional embodiment, the pose determination module 420 may specifically include the following units:

[0160] The pose determination unit is used to transform the first tag coordinates to the standard world coordinate system and determine the second pose matrix of the ultra-wideband tag device in the standard world coordinate system.

[0161] The pose transformation unit is used to transform the second pose matrix based on the extrinsic parameter matrix from the inertial measurement unit to the ultra-wideband tag device, so as to obtain the first pose matrix of the ultra-wideband tag device in the second coordinate system.

[0162] As an optional embodiment, the pose determination unit is specifically used for:

[0163] Based on the first base station coordinates of each ultra-wideband base station in the first coordinate system and the second base station coordinates of each ultra-wideband base station in the standard world coordinate system, determine the transformation matrix from the first coordinate system to the standard world coordinate system.

[0164] Based on the transformation matrix, the coordinates of the first label are converted into the coordinates of the second label in the standard world coordinate system;

[0165] Based on the coordinates of the second tag, determine the yaw angle matrix of the ultra-wideband tag device in the standard world coordinate system;

[0166] Based on the second tag coordinates and the yaw angle matrix, the second pose matrix of the ultra-wideband tag device in the standard world coordinate system is constructed.

[0167] As an optional embodiment, the pose determination unit can also be used for:

[0168] Based on the coordinates of each first base station and each second base station, determine the rotation matrix from the first coordinate system to the standard world coordinate system;

[0169] Based on the target second base station coordinates and the rotation matrix, a transformation matrix is ​​constructed from the first coordinate system to the standard world coordinate system. The target second base station coordinates are the second base station coordinates of the first ultra-wideband base station in the standard world coordinate system.

[0170] As an optional embodiment, the ultra-wideband tag device includes a first ultra-wideband tag device and a second ultra-wideband tag device located symmetrically on both sides of the target vehicle, and the second tag coordinates include the first sub-tag coordinates of the first ultra-wideband tag device and the second sub-tag coordinates of the second ultra-wideband tag device;

[0171] The pose determination unit can also be used for:

[0172] Based on the coordinates of the first sub-label and the second sub-label, determine the difference in the horizontal and vertical coordinates between the coordinates of the first sub-label and the second sub-label.

[0173] Divide the difference in the vertical coordinate by the difference in the horizontal coordinate to obtain the yaw angle of the ultra-wideband tag device in the standard world coordinate system.

[0174] A matrix transformation is performed on the yaw angle to obtain the yaw angle matrix of the ultra-wideband tag device in the standard world coordinate system.

[0175] As an optional embodiment, the pose conversion unit can specifically be used for:

[0176] Obtain the extrinsic parameter matrix from the inertial measurement unit to the ultra-wideband tag device;

[0177] Transpose the extrinsic matrix to obtain the transposed extrinsic matrix;

[0178] Multiplying the transposed extrinsic parameter matrix with the second pose matrix yields the first pose matrix of the ultra-wideband tag device in the second coordinate system.

[0179] As an optional embodiment, the pose determination module 420 may further include the following units:

[0180] The point cloud acquisition unit is used to acquire map reference point cloud and first source point cloud, the first source point cloud being the point cloud collected in real time by the target vehicle sensor;

[0181] Point cloud partitioning unit is used to divide the map reference point cloud into multiple grid spaces and obtain the point cloud mean and point cloud covariance in each grid space.

[0182] The point cloud transformation unit is used to transform the first source point cloud based on the first pose matrix to obtain the second source point cloud;

[0183] The density calculation unit is used to project the second source point cloud onto the corresponding grid space to obtain the joint probability density of the second source point cloud in the map reference point cloud.

[0184] The matrix optimization unit is used to iteratively optimize the first pose matrix according to the joint probability density until a preset stopping condition is met, so as to obtain a sensor pose matrix that matches the target vehicle sensor.

[0185] As an optional embodiment, the vehicle positioning module 430 may specifically include the following units:

[0186] The pose prediction unit is used to integrate the acceleration and angular velocity measured by the inertial measurement unit to obtain the predicted pose of the target vehicle.

[0187] The pose correction unit is used to take the first pose matrix and the sensor pose matrix as the observed pose, correct the state of the predicted pose, and obtain the vehicle positioning result of the target vehicle.

[0188] Based on vehicle positioning methods, this application also provides specific embodiments of vehicle positioning devices.

[0189] Figure 5 A schematic diagram of the hardware structure of the vehicle positioning device provided in an embodiment of this application is shown.

[0190] The vehicle positioning device may include a processor 501 and a memory 502 storing computer program instructions.

[0191] Specifically, the processor 501 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0192] Memory 502 may include mass storage for data or instructions. For example, and not limitingly, memory 502 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 502 may include removable or non-removable (or fixed) media. Where appropriate, memory 502 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 502 is non-volatile solid-state memory.

[0193] The processor 501 implements any of the vehicle positioning methods described in the above embodiments by reading and executing computer program instructions stored in the memory 502.

[0194] In one example, the vehicle positioning device may also include a communication interface 503 and a bus 510. For example, Figure 5 As shown, the processor 501, memory 502, and communication interface 503 are connected through bus 510 and complete communication with each other.

[0195] The communication interface 503 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0196] Bus 510 includes hardware, software, or both, that couples components of the vehicle positioning device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 510 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, any suitable bus or interconnect is contemplated herein.

[0197] Furthermore, in conjunction with the vehicle positioning methods in the above embodiments, this application embodiment can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any of the vehicle positioning methods in the above embodiments.

[0198] In addition, in conjunction with the vehicle positioning method in the above embodiments, this application embodiment can provide a computer program product for implementation. When the instructions in the computer program product are executed by the processor of an electronic device, the electronic device performs the vehicle positioning method provided by any aspect of the above embodiments of this application.

[0199] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0200] The functional blocks shown in the above-described structural diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0201] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0202] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0203] The above description is merely a specific implementation of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

Claims

1. A vehicle positioning method characterized by comprising: include: Obtain the first tag coordinates of the ultra-wideband tag device on the target vehicle in the first coordinate system, wherein the first coordinate system is a plane rectangular coordinate system constructed with the first ultra-wideband base station as the origin; The first tag coordinates are transformed into the second coordinate system to determine the first pose matrix of the ultra-wideband tag device in the second coordinate system, where the second coordinate system is the world coordinate system with the inertial measurement unit as the origin. Based on the first pose matrix, a sensor pose matrix matching the target vehicle sensor is determined, wherein the target vehicle sensor includes at least one of radar and camera; Based on the first pose matrix and the sensor pose matrix, the target vehicle is fused and located to obtain the vehicle positioning result.

2. The method of claim 1, wherein, The step of obtaining the first tag coordinates of the ultra-wideband tag device on the target vehicle in the first coordinate system includes: Obtain the distance between the ultra-wideband tag device and each ultra-wideband base station; The N ultra-wideband base stations with the smallest interval distance are determined as the second ultra-wideband base station, where N is a positive integer not less than 3; The first tag coordinates of the ultra-wideband tag device in the first coordinate system are determined based on the first base station coordinates of each of the second ultra-wideband base stations in the first coordinate system and the interval distance between each of the second ultra-wideband base stations and the ultra-wideband tag device.

3. The method according to claim 1, characterized in that, The step of transforming the first tag coordinates to the second coordinate system and determining the first pose matrix of the ultra-wideband tag device in the second coordinate system includes: Transform the first tag coordinates to the standard world coordinate system to determine the second pose matrix of the ultra-wideband tag device in the standard world coordinate system; Based on the extrinsic parameter matrix from the inertial measurement unit to the ultra-wideband tag device, the second pose matrix is ​​transformed to obtain the first pose matrix of the ultra-wideband tag device in the second coordinate system.

4. The method according to claim 3, characterized in that, The step of transforming the first tag coordinates to the standard world coordinate system and determining the second pose matrix of the ultra-wideband tag device in the standard world coordinate system includes: Based on the first base station coordinates of each ultra-wideband base station in the first coordinate system and the second base station coordinates of each ultra-wideband base station in the standard world coordinate system, determine the transformation matrix from the first coordinate system to the standard world coordinate system. Based on the transformation matrix, the first label coordinates are converted into the second label coordinates in the standard world coordinate system; Based on the second tag coordinates, determine the yaw angle matrix of the ultra-wideband tag device in the standard world coordinate system; Based on the second tag coordinates and the yaw angle matrix, the second pose matrix of the ultra-wideband tag device in the standard world coordinate system is constructed.

5. The method according to claim 4, characterized in that, The step of determining the transformation matrix from the first coordinate system to the standard world coordinate system based on the first base station coordinates of each ultra-wideband base station in the first coordinate system and the second base station coordinates of each ultra-wideband base station in the standard world coordinate system includes: Based on the coordinates of each of the first base stations and the coordinates of each of the second base stations, determine the rotation matrix from the first coordinate system to the standard world coordinate system; Based on the target second base station coordinates and the rotation matrix, a transformation matrix is ​​constructed from the first coordinate system to the standard world coordinate system, wherein the target second base station coordinates are the second base station coordinates of the first ultra-wideband base station in the standard world coordinate system.

6. The method according to claim 4, characterized in that, The ultra-wideband tag device includes a first ultra-wideband tag device and a second ultra-wideband tag device located symmetrically on both sides of the target vehicle. The second tag coordinate includes the first sub-tag coordinate of the first ultra-wideband tag device and the second sub-tag coordinate of the second ultra-wideband tag device. The step of determining the yaw angle matrix of the ultra-wideband tag device in the standard world coordinate system based on the second tag coordinates includes: Based on the coordinates of the first sub-label and the coordinates of the second sub-label, determine the difference in the horizontal coordinate and the difference in the vertical coordinate between the coordinates of the first sub-label and the coordinates of the second sub-label; Divide the difference in the vertical coordinate by the difference in the horizontal coordinate to obtain the yaw angle of the ultra-wideband tag device in the standard world coordinate system. The yaw angle is transformed by matrix transformation to obtain the yaw angle matrix of the ultra-wideband tag device in the standard world coordinate system.

7. The method according to claim 3, characterized in that, The transformation of the second pose matrix based on the extrinsic parameter matrix from the inertial measurement unit to the ultra-wideband tag device to obtain the first pose matrix of the ultra-wideband tag device in the second coordinate system includes: Obtain the extrinsic parameter matrix from the inertial measurement unit to the ultra-wideband tag device; Perform a transpose operation on the extrinsic parameter matrix to obtain the transposed extrinsic parameter matrix; Multiplying the transposed extrinsic parameter matrix with the second pose matrix yields the first pose matrix of the ultra-wideband tag device in the second coordinate system.

8. The method according to any one of claims 1-7, characterized in that, The step of determining the sensor pose matrix matching the target vehicle sensor based on the first pose matrix includes: Acquire map reference point cloud and first source point cloud, wherein the first source point cloud is the point cloud collected in real time by the target vehicle-mounted sensor; The map reference point cloud is divided into multiple grid spaces, and the point cloud mean and point cloud covariance in each grid space are obtained. Based on the first pose matrix, the first source point cloud is transformed to obtain the second source point cloud; The second source point cloud is projected onto the corresponding grid space to obtain the joint probability density of the second source point cloud in the map reference point cloud; Based on the joint probability density, the first pose matrix is ​​iteratively optimized until a preset stopping condition is met, thereby obtaining a sensor pose matrix that matches the target vehicle sensor.

9. The method according to any one of claims 1-7, characterized in that, The step of fusing and locating the target vehicle based on the first pose matrix and the sensor pose matrix to obtain the vehicle localization result includes: The acceleration and angular velocity measured by the inertial measurement unit are integrated to obtain the predicted pose of the target vehicle; Using the first pose matrix and the sensor pose matrix as the observed pose, the predicted pose is state-corrected to obtain the vehicle positioning result of the target vehicle.

10. A vehicle positioning device, characterized in that, include: The coordinate acquisition module is used to acquire the first tag coordinates of the ultra-wideband tag device on the target vehicle in the first coordinate system, wherein the first coordinate system is a plane rectangular coordinate system constructed with the first ultra-wideband base station as the origin; The pose determination module is used to transform the first tag coordinates to a second coordinate system and determine the first pose matrix of the ultra-wideband tag device in the second coordinate system, wherein the second coordinate system is a world coordinate system with the inertial measurement unit as the origin; The pose determination module is further configured to determine a sensor pose matrix that matches the target vehicle sensor based on the first pose matrix, wherein the target vehicle sensor includes at least one of radar and camera. The vehicle positioning module is used to perform fusion positioning of the target vehicle based on the first pose matrix and the sensor pose matrix to obtain the vehicle positioning result of the target vehicle.

11. A computer program product, characterized in that, When the instructions in the computer program product are executed by the processor of the electronic device, the electronic device performs the vehicle positioning method as described in any one of claims 1-9.

Images