Vehicle positioning method, automatic parking method, electronic equipment and vehicle

Abstract

The invention discloses a vehicle positioning method, an automatic parking method, electronic equipment and a vehicle, and relates to the technical field of vehicles. The method comprises the following steps: controlling a vehicle to send ultra-wideband signals to a master base station and at least two slave base stations so as to obtain the distance between the vehicle and the base stations and further obtain the position of the vehicle and an azimuth angle relative to a preset reference point; obtaining the acceleration of the vehicle, and obtaining an initial observation vector according to the position, the azimuth angle and the acceleration; acquiring a first moment when the ultra-wideband signal arrives at the master base station and a second moment when the ultra-wideband signal arrives at the slave base station, and calculating a difference value between the first moment and the second moment to obtain an arrival time difference; obtaining an arrival time difference variance according to the arrival time difference; and correcting the initial observation vector according to the time difference of arrival variance and the signal intensity of the ultra-wideband signal to obtain a final observation vector, and obtaining a positioning result of the vehicle according to the final observation vector. According to the method, high-precision vehicle positioning can be realized.

Description

Technical Field

[0001] This invention relates to the field of vehicle technology, and more particularly to a vehicle positioning method, an automatic parking method, electronic equipment, and a vehicle. Background Technology

[0002] The vehicle positioning in related technologies uses static parameters, but static parameters cannot adapt to sudden interference, which can lead to insufficient vehicle positioning accuracy. Summary of the Invention

[0003] This invention aims to at least partially solve one of the technical problems in related technologies. Therefore, the first objective of this invention is to provide a vehicle positioning method to achieve high-precision vehicle positioning.

[0004] The second objective of this invention is to provide an automatic parking method.

[0005] The third objective of this invention is to provide an electronic device.

[0006] The fourth objective of this invention is to provide a vehicle.

[0007] To achieve the above objectives, a first aspect of the present invention provides a vehicle positioning method, the method comprising: controlling a vehicle to send an ultra-wideband signal to at least three preset base stations to obtain the distance between the vehicle and the at least three preset base stations, wherein the at least three preset base stations include one master base station and at least two slave base stations; obtaining the position of the vehicle and the azimuth angle of the vehicle relative to a preset reference point based on the distance; obtaining the acceleration of the vehicle using an inertial measurement unit, and obtaining an initial observation vector based on the position, the azimuth angle, and the acceleration; acquiring a first moment when the ultra-wideband signal arrives at the master base station, and acquiring at least two second moments when the ultra-wideband signal arrives at at least two of the slave base stations, calculating the difference between the first moment and the at least two second moments to obtain at least two arrival time differences; obtaining the arrival time difference variance based on the arrival time differences; correcting the initial observation vector based on the arrival time difference variance and the signal strength of the ultra-wideband signal to obtain a final observation vector, and obtaining the vehicle positioning result based on the final observation vector.

[0008] The vehicle positioning method according to embodiments of the present invention can locate a vehicle. Moreover, during positioning, the initial observation vector is corrected by using the time difference of arrival variance and the signal strength of the ultra-wideband signal, so as to avoid insufficient positioning accuracy due to the inability of static parameters to adapt to dynamic interference, thereby achieving high-precision vehicle positioning.

[0009] In addition, the vehicle positioning method according to embodiments of the present invention may also have the following additional technical features: According to one embodiment of the present invention, the step of correcting the initial observation vector based on the time difference of arrival variance and the signal strength of the ultra-wideband signal includes: inputting the time difference of arrival variance and the signal strength into a preset fully connected neural network to obtain an error correction amount; and correcting the initial observation vector based on the error correction amount to obtain the final observation vector.

[0010] According to one embodiment of the present invention, the activation function of the preset fully connected neural network is a modified linear unit.

[0011] According to one embodiment of the present invention, the error correction amount is obtained according to the following formula: , in, The activation function is... This is the error correction amount. The signal strength, Let the variance of the arrival time difference be... For acceleration variance, These are the hidden layer weights of the preset fully connected neural network. The output layer weights of the preset fully connected neural network, For hidden layer bias, This is the output layer bias.

[0012] According to one embodiment of the present invention, obtaining the positioning result of the vehicle based on the final observation vector includes: acquiring the state vector of the vehicle; and processing the state vector and the final observation vector using an adaptive unscented Kalman filter algorithm to obtain the positioning result.

[0013] According to one embodiment of the present invention, the number of slave base stations is three.

[0014] According to one embodiment of the present invention, the state vector includes the vehicle's speed and position in a preset coordinate system.

[0015] To achieve the above objectives, a second aspect of the present invention provides an automatic parking method, the method comprising: using the above-described vehicle positioning method to obtain a vehicle positioning result; and controlling the vehicle to park based on the positioning result.

[0016] According to the automatic parking method of the present invention, the vehicle is located by using the vehicle positioning method of the above embodiment, and parking is performed according to the positioning result. During positioning, the initial observation vector can be corrected by using the variance of the time difference of arrival and the signal strength of the ultra-wideband signal, so as to avoid insufficient positioning accuracy due to the inability of static parameters to adapt to dynamic interference, thereby achieving high-precision parking.

[0017] To achieve the above objectives, a third aspect of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the computer program is executed by the processor, it implements the above-described vehicle positioning method or the above-described vehicle parking method.

[0018] The electronic device according to the embodiments of the present invention can achieve high-precision vehicle positioning by implementing the vehicle positioning method of the above embodiments or the automatic parking method of the above embodiments, and thus achieve high-precision vehicle parking when implementing the automatic parking method of the above embodiments.

[0019] To achieve the above objectives, a fourth aspect of the present invention provides a vehicle including the aforementioned electronic equipment.

[0020] According to the vehicle of the present invention, high-precision vehicle positioning can be achieved through the electronic equipment described above, thereby achieving high-precision vehicle parking when automatic parking is implemented.

[0021] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0022] Figure 1 This is a flowchart of a vehicle positioning method according to an embodiment of the present invention; Figure 2 This is a schematic diagram of a vehicle positioning method according to an example of the present invention; Figure 3 This is a flowchart of an automatic parking method according to an embodiment of the present invention; Figure 4 This is a schematic diagram of an example of an automatic parking method according to the present invention; Figure 5 This is a structural block diagram of an electronic device according to an embodiment of the present invention; Figure 6 This is a structural block diagram of a vehicle according to an embodiment of the present invention. Detailed Implementation

[0023] The vehicle positioning method, automatic parking method, electronic device, and vehicle of the present invention are described below with reference to the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described with reference to the accompanying drawings are exemplary and should not be construed as limiting the present invention.

[0024] Figure 1 This is a flowchart of a vehicle positioning method according to an embodiment of the present invention.

[0025] like Figure 1 As shown, the vehicle positioning method includes: S11, control the vehicle to send ultra-wideband signals to at least three preset base stations to obtain the distance between the vehicle and at least three preset base stations, wherein the at least three preset base stations include one master base station and at least two slave base stations.

[0026] Specifically, the aforementioned controlled vehicle sends ultra-wideband signals to at least three preset base stations to obtain the distance between the vehicle and at least three preset base stations. This can be achieved by the vehicle sending ultra-wideband signals to the base stations, and after the base stations receive the ultra-wideband signals, they obtain the distance between the vehicle and the base stations based on the time when the ultra-wideband signals are received and the time when the vehicle sends the ultra-wideband signals.

[0027] Alternatively, the vehicle can send an ultra-wideband (UWB) signal to the base station. After receiving the UWB signal, the base station then sends an UWB signal back to the vehicle. The vehicle can then determine the distance between itself and the base station based on the times it sends and receives the UWB signal.

[0028] Alternatively, the base station can send an ultra-wideband (UWB) signal to the vehicle. After receiving the UWB signal, the vehicle then sends an UWB signal back to the base station. The base station can then determine the distance between the vehicle and the base station based on the times when the UWB signal is sent and received.

[0029] S12, obtain the vehicle's position and azimuth angle relative to the preset reference point based on the distance.

[0030] As an example, after obtaining the distance between the vehicle and at least three preset base stations, the vehicle's eastward and northward positions relative to the preset coordinate origin can be obtained based on these distances, and the vehicle's azimuth angle relative to the preset reference point can be obtained.

[0031] To obtain the aforementioned azimuth angle, a preset reference point can be set, and then a line can be established between the vehicle and the preset reference point. This allows us to obtain the rotation angle when rotating from due north to the line, which is the azimuth angle.

[0032] S13 uses an inertial measurement unit to obtain the vehicle's acceleration and obtains the initial observation vector based on the position, azimuth angle, and acceleration.

[0033] Specifically, an inertial measurement unit is installed on the vehicle, and the accelerometer of the inertial measurement unit is used to obtain the vehicle's acceleration. Then, the vehicle's acceleration collected by the inertial measurement unit is integrated to obtain the vehicle's displacement. Finally, an initial observation vector is obtained based on the vehicle's position, azimuth angle, and displacement.

[0034] As an example, the above initial observation vector ,Should As the initial observation vector, it provides actual UWB (Ultra-Wideband) ranging results and IMU (Inertial Measurement Unit) acceleration to correct prediction errors driven by pure models.

[0035] Among them, the above The eastward coordinates are UWB observations, representing the eastward position measured by the ultra-wideband positioning system, typically expressed in meters (m).

[0036] The above These are UWB north-direction coordinate observations, representing the north-direction position measured by the ultra-wideband positioning system, typically expressed in meters (m).

[0037] The above The IMU velocity integral is the displacement obtained by integrating the acceleration measured by the accelerometer, with units measured in meters (m). Optionally, the above... It can also be the integral of displacement.

[0038] The above The azimuth angle is the UWB azimuth angle measured by the ultra-wideband positioning system relative to the reference point, and the unit is radians.

[0039] S14, obtain the first time when the ultra-wideband signal arrives at the main base station, and obtain at least two second times when the ultra-wideband signal arrives at at least two slave base stations, calculate the difference between the first time and the at least two second times, and obtain at least two arrival time differences.

[0040] Specifically, after obtaining the initial observation vector, in order to avoid insufficient positioning accuracy due to the inability of static parameters to adapt to dynamic interference, the first moment when the ultra-wideband signal arrives at the main base station and the second moment when it arrives at the slave base station after the vehicle sends the ultra-wideband signal are obtained.

[0041] The first and second moments mentioned above can be obtained by using the timestamp of the ultra-wideband signal arriving at the base station.

[0042] Since the number of base stations is at least two, the number of the aforementioned second time points is at least two.

[0043] After obtaining the first and second moments, for each second moment, the difference between the first and second moments is calculated to obtain the arrival time difference.

[0044] It should be noted that since the vehicle may have sent an ultra-wideband signal more than once when its location is obtained, the time difference of arrival corresponding to each ultra-wideband signal sent by the vehicle can be obtained.

[0045] S15, the variance of arrival time difference is obtained based on the arrival time difference.

[0046] Specifically, after obtaining the arrival time difference, the variance is calculated for all the obtained arrival time differences to obtain the arrival time difference variance.

[0047] S16. The initial observation vector is corrected based on the variance of the time difference of arrival and the signal strength of the ultra-wideband signal to obtain the final observation vector, and the vehicle positioning result is obtained based on the final observation vector.

[0048] Specifically, after obtaining the time difference variance, the initial observation vector can be corrected based on the time difference variance and the signal strength of the ultra-wideband signal to obtain the final observation vector, thereby avoiding insufficient positioning accuracy due to the inability of static parameters to adapt to dynamic interference.

[0049] After obtaining the final observation vector, the vehicle's positioning result can be obtained based on the final observation vector.

[0050] Therefore, vehicle positioning can be achieved. Moreover, during positioning, the initial observation vector is corrected by using the time difference of arrival variance and the signal strength of the ultra-wideband signal, so as to avoid insufficient positioning accuracy due to the inability of static parameters to adapt to dynamic interference, thereby achieving high-precision vehicle positioning.

[0051] In some embodiments of the present invention, the initial observation vector is corrected based on the time difference of arrival variance and the signal strength of the ultra-wideband signal, including: inputting the time difference of arrival variance and the signal strength into a preset fully connected neural network to obtain an error correction amount; and correcting the initial observation vector based on the error correction amount to obtain the final observation vector.

[0052] The following description uses a specific example.

[0053] In this specific embodiment, the activation function of the pre-defined fully connected neural network is a modified linear unit. The aforementioned error correction amount is the NLOS (Non-Line-Of-Sight) error correction amount.

[0054] Specifically, the aforementioned preset fully connected neural network is configured as a three-layer fully connected neural network. The inputs of this fully connected neural network are signal strength, time difference of arrival variance, and IMU acceleration variance. The IMU acceleration variance can be a pre-obtained acceleration variance or a variance calculated in real time based on the measured acceleration. The output of this fully connected neural network is the NLOS error correction amount. .

[0055] The error correction amount can be obtained according to the following formula: , in, For activation function, This is the error correction amount. For signal strength, For the variance of arrival time difference, For acceleration variance, To pre-define the hidden layer weights of a fully connected neural network, To preset the output layer weights of a fully connected neural network, For hidden layer bias, This is the output layer bias.

[0056] In other words, this application does not limit the specific structure of the above three-layer fully connected neural network, as long as it can achieve the result obtained in the above formula. That's all.

[0057] After obtaining the error correction amount Then, the initial observation vector can be corrected according to the error correction amount to obtain the final observation vector. Specifically, it can be expressed as follows: , in, This is the final observation vector.

[0058] In some embodiments of the present invention, obtaining the vehicle's localization result based on the final observation vector includes: acquiring the vehicle's state vector, and processing the state vector and the final observation vector using an adaptive unscented Kalman filter algorithm to obtain the localization result.

[0059] The following description uses a specific example.

[0060] In this specific embodiment, a state vector is first obtained, which includes the vehicle's speed and position in a preset coordinate system, which is a geographic coordinate system.

[0061] Specifically, the state vector described above is as follows: , in, Let E be the state vector, used to predict the prior state based on the state estimate from the previous time step. E represents the eastward position component of the vehicle in the geographic coordinate system, in meters, and N represents the northward position component of the vehicle in the geographic coordinate system, in meters. This represents the velocity component of the object in the eastward direction, measured in meters per second. This indicates the vehicle's velocity component in the north direction, expressed in meters per second.

[0062] Furthermore, after obtaining the state vector and the final observation vector, an adaptive unscented Kalman filter algorithm can be used to process the state vector and the final observation vector to obtain the accurate vehicle position. For example, the state vector and the final observation vector can be fused, and the fused result can be filtered.

[0063] In the process of employing the adaptive unscented Kalman filter algorithm, the state equation and observation equation are as follows: , in, This is the process noise vector, describing the uncertainty of the system model (including sensor errors and external disturbances). Let f be the observation noise vector, describing the error of the UWB ranging device noise. f() is the nonlinear state transition function, and h() is the nonlinear observation function.

[0064] When generating Sigma points, select Sigma points The weights are: , in, n is the state dimension, representing the length of the state vector (a 4-dimensional state vector). (corresponding to n=4) α is the distribution adjustment factor, which controls the distribution range of the Sigma points around the mean (1e-3≤α≤1); k1 is the scaling parameter, which is used to ensure the positive semidefiniteness of the covariance (takes 0 or 3-n). These are composite parameters used for weight calculation; For the i-th Sigma point Weighting coefficients in state prediction; For the 0th Sigma point Weighting coefficients in state prediction; is the covariance weight, representing the weighting coefficient of the Sigma point in the covariance calculation.

[0065] During prediction and updating, Sigma points are propagated through UT (Unscented Transform) to calculate the predicted mean and covariance: , , in, To predict the mean state, a weighted average state estimate is obtained through Sigma point propagation. To predict the covariance matrix, we calculate the state error covariance at the Sigma points, plus the process noise. . The aforementioned nonlinear state transition function is used to describe the system dynamics.

[0066] Similarly, the observation update is performed, and finally the Kalman gain is calculated and the state is corrected.

[0067] When performing noise covariance adaptation, based on the innovation sequence Dynamic adjustment and .

[0068] in, Indicates from The observable components are extracted from the state vector at each time step. To observe the noise covariance matrix and characterize the sensor error. This is the process noise covariance matrix, describing the IMU integration error and motion abrupt changes.

[0069] Adjustment: The theoretical prediction error is subtracted from the covariance of the new information sequence to avoid over-correction.

[0070] Adjustment: The observation error is backpropagated to the process noise through Kalman gain.

[0071]

[0072] in, As the attenuation factor, , , This is the observation matrix. This is the theoretical prediction error. For Kalman gain.

[0073] Therefore, by using the modified final observation vector during adaptive unscented Kalman filtering, the modification of the observation vector directly affects the innovation sequence, which can effectively achieve dynamic error compensation and improve the accuracy and robustness of UWB in complex environments.

[0074] In some embodiments of the present invention, see Figure 2 The example shown has three base stations, meaning the total number of base stations is four.

[0075] In summary, the vehicle positioning method of this invention involves controlling a vehicle to send ultra-wideband signals to at least three preset base stations to obtain the distance between the vehicle and the at least three preset base stations, wherein the at least three preset base stations include one master base station and at least two slave base stations; obtaining the vehicle's position and azimuth angle relative to a preset reference point based on the distance; obtaining the vehicle's acceleration using an inertial measurement unit, and obtaining an initial observation vector based on the position, azimuth angle, and acceleration; acquiring the first moment when the ultra-wideband signal arrives at the master base station, and acquiring at least two second moments when the ultra-wideband signal arrives at the at least two slave base stations, calculating the difference between the first moment and the at least two second moments to obtain at least two arrival time differences; obtaining the arrival time difference variance based on the arrival time difference; correcting the initial observation vector based on the arrival time difference variance and the signal strength of the ultra-wideband signal to obtain the final observation vector, and obtaining the vehicle positioning result based on the final observation vector. Therefore, vehicle positioning can be achieved. Moreover, during positioning, the initial observation vector is corrected using the arrival time difference variance and the signal strength of the ultra-wideband signal, avoiding insufficient positioning accuracy due to static parameters being unable to adapt to dynamic interference, thereby achieving high-precision vehicle positioning.

[0076] Furthermore, this invention proposes an automatic parking method.

[0077] Figure 3 This is a flowchart of an automatic parking method according to an embodiment of the present invention.

[0078] like Figure 3 As shown, the automatic parking method includes: S31. Using the vehicle positioning method described above, the vehicle positioning result is obtained.

[0079] S32 controls vehicle parking based on positioning results.

[0080] The following description uses a specific example.

[0081] See Figure 4 In this specific embodiment, UWB is integrated into the vehicle's digital key platform, and the user's remote control device is also configured to support UWB.

[0082] At this point, the user can send remote parking start / pause commands, access to available functions, and other possible commands via the remote control. The commands sent by the remote control will be transmitted to the vehicle's digital key platform.

[0083] The vehicle is also equipped with a parking controller and lateral and longitudinal actuators. The lateral and longitudinal actuators are used to control the movement of the vehicle, and the parking controller is used to send acceleration / deceleration requests or other possible signals to the lateral and longitudinal actuators to control the lateral and longitudinal actuators and realize the parking of the vehicle.

[0084] The aforementioned parking controller is also used to interact with the vehicle's digital key platform to send the current parking status to the digital key platform.

[0085] The interaction information between the aforementioned digital key platform and the parking controller can send requests to the parking controller for remote parking mode, parking start / pause commands, parking status, available parking functions, and other possible information.

[0086] The automatic parking method of this invention uses the vehicle positioning method of the above embodiment to locate the vehicle and then park it according to the positioning result. During positioning, the initial observation vector can be corrected by using the variance of the time difference of arrival and the signal strength of the ultra-wideband signal, so as to avoid insufficient positioning accuracy due to the inability of static parameters to adapt to dynamic interference, thereby achieving high-precision parking.

[0087] Furthermore, the present invention proposes an electronic device.

[0088] Figure 5 This is a structural block diagram of an electronic device according to an embodiment of the present invention.

[0089] like Figure 5 As shown, the electronic device 500 includes a processor 501 and a memory 503. The processor 501 and the memory 503 are connected, for example, via a bus 502. Optionally, the electronic device 500 may also include a transceiver 504. It should be noted that in practical applications, the transceiver 504 is not limited to one type, and the structure of this electronic device 500 does not constitute a limitation on the embodiments of the present invention.

[0090] Processor 501 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this invention. Processor 501 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0091] Bus 502 may include a pathway for transmitting information between the aforementioned components. Bus 502 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 502 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 5 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0092] The memory 503 stores a computer program corresponding to the vehicle positioning method and / or automatic parking method of the above embodiments of the present invention. This computer program is controlled and executed by the processor 501. The processor 501 executes the computer program stored in the memory 503 to implement the content shown in the foregoing method embodiments.

[0093] in, Figure 5 The electronic device 500 shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0094] The electronic device of this invention can achieve high-precision vehicle positioning by implementing the vehicle positioning method of the above embodiments or the automatic parking method of the above embodiments, and thus achieve high-precision vehicle parking when implementing the automatic parking method of the above embodiments.

[0095] Furthermore, the present invention proposes a vehicle.

[0096] Figure 6 This is a structural block diagram of a vehicle according to an embodiment of the present invention.

[0097] like Figure 6 As shown, vehicle 10 includes the aforementioned electronic equipment 500.

[0098] The vehicle in this embodiment of the invention, through the electronic equipment described above, can achieve high-precision vehicle positioning, thereby achieving high-precision vehicle parking when implementing automatic parking.

[0099] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein can be considered as a ordered list of executable instructions for implementing logical functions, which can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0100] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0101] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0102] In the description of this specification, the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," and "circumferential" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and should not be construed as limiting the present invention.

[0103] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0104] In this specification, unless otherwise stated, the terms "installation," "connection," "joining," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components, unless otherwise explicitly defined. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0105] In this invention, unless otherwise explicitly specified and limited, "above" or "below" the second feature can mean that the first feature is in direct contact with the second feature, or that the first feature is in indirect contact with the second feature through an intermediate medium. Furthermore, "above," "over," and "on top" of the second feature can mean that the first feature is directly above or diagonally above the second feature, or simply that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature can mean that the first feature is directly below or diagonally below the second feature, or simply that the first feature is at a lower horizontal level than the second feature.

[0106] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A vehicle positioning method, characterized in that, The method includes: The vehicle is controlled to send ultra-wideband signals to at least three preset base stations to obtain the distance between the vehicle and the at least three preset base stations, wherein the at least three preset base stations include one master base station and at least two slave base stations; The position of the vehicle and the azimuth angle of the vehicle relative to a preset reference point are obtained based on the distance. The vehicle's acceleration is obtained using an inertial measurement unit, and an initial observation vector is obtained based on the position, the azimuth angle, and the acceleration. The first time when the ultra-wideband signal arrives at the main base station is obtained, and at least two second times when the ultra-wideband signal arrives at at least two of the slave base stations are obtained. The difference between the first time and the at least two second times is calculated to obtain at least two arrival time differences. The variance of the arrival time difference is obtained based on the arrival time difference. The initial observation vector is corrected based on the time difference of arrival variance and the signal strength of the ultra-wideband signal to obtain the final observation vector, and the vehicle positioning result is obtained based on the final observation vector.

2. The vehicle positioning method according to claim 1, characterized in that, The step of correcting the initial observation vector based on the variance of the time difference of arrival and the signal strength of the ultra-wideband signal includes: The time difference of arrival variance and the signal strength are input into a preset fully connected neural network to obtain the error correction amount; The initial observation vector is corrected according to the error correction amount to obtain the final observation vector.

3. The vehicle positioning method according to claim 2, characterized in that, The activation function of the preset fully connected neural network is the modified linear unit.

4. The vehicle positioning method according to claim 3, characterized in that, The error correction amount is obtained according to the following formula: ， in, The activation function is... This is the error correction amount. The signal strength, Let the variance of the arrival time difference be... For acceleration variance, These are the hidden layer weights of the preset fully connected neural network. The output layer weights of the preset fully connected neural network, For hidden layer bias, This is the output layer bias.

5. The vehicle positioning method according to claim 1, characterized in that, The step of obtaining the vehicle's positioning result based on the final observation vector includes: Obtain the state vector of the vehicle; The state vector and the final observation vector are processed using an adaptive unscented Kalman filter algorithm to obtain the localization result.

6. The vehicle positioning method according to claim 1, characterized in that, The number of slave base stations is three.

7. The vehicle positioning method according to claim 5, characterized in that, The state vector includes the vehicle's speed and its position in a preset coordinate system.

8. An automatic parking method, characterized in that, The method includes: The vehicle positioning result is obtained by using the vehicle positioning method according to any one of claims 1-7; The vehicle is parked based on the positioning results.

9. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and running on the processor, wherein when the computer program is executed by the processor, it implements the vehicle positioning method according to any one of claims 1-7, or implements the vehicle parking method according to claim 8.

10. A vehicle, characterized in that, Including the electronic device according to claim 9.

Images