Fusion positioning methods, devices, processors, storage media, and electronic devices

Abstract

This invention relates to the field of vehicle positioning, and discloses a fusion positioning method, apparatus, processor, storage medium, and electronic device, relating to the field of vehicle positioning technology. The method includes: acquiring measurement data and observation data of the vehicle, wherein the measurement data is data obtained from the vehicle's gyroscope and wheel speedometer, and the observation data is data observed from multiple positioning sensors of the vehicle positioning system; determining first information of the vehicle based on the measurement data, wherein the first information is used to update the vehicle's target information, and the target information represents the vehicle's positioning information; determining second information of the vehicle based on the first information and a correspondence; fusing the observation data and the second information according to a fusion strategy to obtain updated information; and merging the first information and the updated information to obtain the target information. This invention solves the technical problem of low positioning accuracy caused by using a single positioning method for vehicle positioning in related technologies.

Description

Technical Field

[0001] This invention relates to the field of vehicle positioning technology, and more specifically, to a fusion positioning method, apparatus, processor, storage medium, and electronic device. Background Technology

[0002] With the development of autonomous driving technology, the requirements for vehicle positioning accuracy are becoming increasingly higher. High-precision positioning algorithms can provide accurate vehicle position information for the entire autonomous driving system, thereby accurately determining the vehicle's pose and motion state, which is one of the key factors to ensure that the vehicle can operate safely and smoothly.

[0003] Currently, autonomous driving systems use a satellite-inertial navigation system (SINa) based on strapdown inertial navigation system (SINS) for vehicle positioning. However, this system may fail to locate vehicles in obstructed areas due to the inability to effectively receive satellite signals. LiDAR-based point cloud matching positioning algorithms can effectively solve the positioning problem in obstructed areas, but in large open areas or long tunnels, this algorithm may fail due to the lack of obvious feature points in the LiDAR point cloud data.

[0004] There is currently no effective solution to the above problems. Summary of the Invention

[0005] This invention provides a fusion positioning method, apparatus, processor, storage medium, and electronic device to at least solve the technical problem of low positioning accuracy caused by using a single positioning method to locate vehicles in related technologies.

[0006] According to one embodiment of the present invention, a fusion positioning method is provided, comprising:

[0007] The system acquires measurement and observation data of the vehicle. Measurement data is obtained from the vehicle's gyroscope and wheel speedometer, while observation data is obtained from various positioning sensors in the vehicle positioning system. Based on the measurement data, the system determines first information about the vehicle, which is used to update the vehicle's target information and represents its positioning information. Based on the first information and a corresponding relationship, the system determines second information about the vehicle, which represents the relationship between the first information, the second information, and the target information. The second information is used to update the measurement error of the vehicle positioning system. The system fuses the observation data and the second information according to a fusion strategy to obtain updated information, which represents the updated second information. Finally, the system merges the first information and the updated information to obtain the target information.

[0008] Optionally, the updated information obtained by fusing observation data and second information according to the fusion strategy includes: fusing first observation data and second information according to the fusion strategy to obtain first updated information, wherein the first observation data is data observed by the first positioning sensor; and fusing second observation data and first updated information according to the fusion strategy to obtain second updated information, wherein the second observation data is data observed by the second positioning sensor, and the multiple positioning sensors include the first positioning sensor and the second positioning sensor.

[0009] Optionally, merging the first information with the updated information to obtain the target information includes merging the first information with the second updated information to obtain the target information.

[0010] Optionally, acquiring vehicle measurement data includes: acquiring the vehicle's angular velocity using a gyroscope; and acquiring the vehicle's speed using a wheel speed meter.

[0011] Optionally, determining the first information of the vehicle based on the measurement data includes integrating the angular velocity and the velocity to obtain the first information.

[0012] Alternatively, a variety of positioning sensors may be used, including lidar, GPS, photographic equipment, and mapping equipment.

[0013] According to one embodiment of the present invention, a fusion positioning device is also provided, comprising:

[0014] The system comprises the following modules: an acquisition module, which acquires measurement data and observation data of the vehicle, wherein the measurement data is obtained from the vehicle's gyroscope and wheel speedometer, and the observation data is obtained from various positioning sensors of the vehicle positioning system; a determination module, which determines first information of the vehicle based on the measurement data, wherein the first information is used to update the vehicle's target information, and the target information represents the vehicle's positioning information; the determination module also determines second information of the vehicle based on the first information and a correspondence, wherein the correspondence represents the relationship between the first information, the second information, and the target information, and the second information is used to update the measurement error of the vehicle positioning system; a fusion module, which fuses the observation data and the second information according to a fusion strategy to obtain updated information, wherein the fusion strategy is used to update the second information, and the updated information represents the updated second information; and a merging module, which merges the first information and the updated information to obtain the target information.

[0015] Optionally, the acquisition module is also used to acquire the angular velocity of the vehicle based on the gyroscope and the speed of the vehicle based on the wheel speed meter.

[0016] Optionally, the determining module is also used to integrate the angular velocity and velocity to obtain the first information.

[0017] Optionally, the fusion module is further configured to fuse the first observation data and the second information according to the fusion strategy to obtain the first update information, wherein the first observation data is data observed by the first positioning sensor; and to fuse the second observation data and the first update information according to the fusion strategy to obtain the second update information, wherein the second observation data is data observed by the second positioning sensor, and the multiple positioning sensors include the first positioning sensor and the second positioning sensor.

[0018] Optionally, the merging module is also used to merge the first information with the second updated information to obtain the target information.

[0019] Alternatively, a variety of positioning sensors may be used, including lidar, GPS, photographic equipment, and mapping equipment.

[0020] According to one embodiment of the present invention, a processor is also provided, the processor being used to run a program, wherein the program is configured to execute the fusion positioning method of any of the above-mentioned methods during runtime.

[0021] According to one embodiment of the present invention, a computer-readable storage medium is also provided, wherein the storage medium stores a computer program, wherein the computer program is configured to execute the fusion positioning method described above when running on a computer or processor.

[0022] According to one embodiment of the present invention, an electronic device is also provided, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the fusion positioning method described in any of the preceding claims.

[0023] In this embodiment of the invention, measurement data is obtained from the vehicle's gyroscope and wheel speedometer, and observation data is obtained from multiple positioning sensors of the vehicle positioning system. First information for updating the vehicle's positioning information is determined based on the measurement data. Second information for updating the measurement error of the vehicle positioning system is then determined based on the first information and a correspondence relationship, where the correspondence relationship represents the relationship between the first information, the second information, and the target information (vehicle positioning information). The observation data and the second information are fused according to a fusion strategy to obtain updated information, where the fusion strategy updates the second information, and the updated information represents the updated second information. Finally, the first information and the updated information are merged to obtain the target information (vehicle positioning information). This achieves the goal of high-precision vehicle positioning by fusing data from multiple positioning sensors. The method is robust and has low implementation cost. Furthermore, the method is not limited by special scenarios, avoiding inaccurate vehicle positioning results in special scenarios, thus improving vehicle positioning accuracy and solving the technical problem of low positioning accuracy caused by using a single positioning method for vehicle positioning in related technologies. Attached Figure Description

[0024] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0025] Figure 1 This is a flowchart of a fusion positioning method according to one embodiment of the present invention;

[0026] Figure 2 This is a schematic diagram of the overall system architecture of the fusion positioning method according to one embodiment of the present invention;

[0027] Figure 3 This is a structural block diagram of a lidar point cloud matching module according to one embodiment of the present invention;

[0028] Figure 4 This is a structural block diagram of a fusion positioning device according to one embodiment of the present invention. Detailed Implementation

[0029] For ease of understanding, some concepts related to the embodiments of the present invention are explained by way of example for reference.

[0030] As shown below:

[0031] An inertial measurement unit (IMU) mainly consists of a gyroscope and an accelerometer, used to measure an object's three-axis attitude angles (or angular velocities) and acceleration. The gyroscope measures the object's angular velocity and acceleration in three-dimensional space, and uses this to calculate the object's attitude. The accelerometer detects the object's acceleration signals along the three independent axes of the carrier coordinate system.

[0032] Heading angle: In a ground coordinate system, the angle between the vehicle's center of gravity velocity and the horizontal axis, which can be used to represent the vehicle's direction in three-dimensional space.

[0033] Kalman filtering is an algorithm that uses the state equations of a linear system to optimally estimate the system state based on the system's input and output observation data. Since the observation data includes noise and interference from the system, the optimal estimation can also be viewed as a filtering process. Kalman filtering algorithms include direct and indirect methods. In this embodiment, the vehicle is located (fused localization) using an indirect Kalman filtering algorithm. The vehicle's true state is decomposed into two forms: an integral state and an error state. In the integral state, the vehicle's localization information is unaffected by system uncertainty; in the error state, the vehicle's localization information is affected by system uncertainty. The localization information from the integral state and the error state is combined to obtain the vehicle's true localization information, which is the final localization information needed for vehicle localization.

[0034] Point cloud data refers to a set of vectors in a three-dimensional coordinate system. Scanned data is recorded in the form of points, each containing three-dimensional coordinates, and some may contain color information (RGB) or reflectance intensity information (Intensity).

[0035] Jacobian matrix: In vector calculus, the Jacobian matrix is ​​a matrix in which first-order partial derivatives are arranged in a certain way. Its determinant is called the Jacobian determinant. Its importance lies in the fact that it represents the optimal linear approximation of a differentiable equation to a given point. Therefore, the Jacobian matrix is ​​similar to the derivative of a multivariable function.

[0036] Cross product mapping: This is a binary algorithm for vectors in a vector space. The cross product mapping of vector a can be expressed as:

[0037]

[0038] Among them, a x Let a represent the projection of vector a onto the x-axis. y This represents the projection of vector a onto the y-axis, a z This represents the projection of vector a onto the z-axis.

[0039] State transition matrix: A matrix in control theory that is a function of time and initial time. The state vector at time can be obtained by multiplying this matrix by the state vector at time.

[0040] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0041] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0042] According to one embodiment of the present invention, an embodiment of the fusion positioning method is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0043] This method embodiment can be executed in an electronic device, similar control device, or system that includes a memory and a processor, located in a vehicle. Taking an electronic device as an example, the electronic device may include one or more processors and a memory for storing data. Optionally, the electronic device may also include communication equipment for communication functions and a display device. Those skilled in the art will understand that the above structural description is merely illustrative and does not limit the structure of the electronic device. For example, the electronic device may include more or fewer components than described above, or have a different configuration than described above.

[0044] A processor may include one or more processing units. For example, a processor may include a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processing (DSP) chip, a microcontroller unit (MCU), a field-programmable gate array (FPGA), a neural network processing unit (NPU), a tensor processing unit (TPU), or an artificial intelligence (AI) processor. Different processing units may be independent components or integrated into one or more processors. In some instances, electronic devices may also include one or more processors.

[0045] The memory can be used to store computer programs, such as the computer program corresponding to the fusion positioning method in this embodiment of the invention. The processor implements the fusion positioning method by running the computer program stored in the memory. The memory may include high-speed random access memory and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to electronic devices via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0046] Communication devices are used to receive or send data via a network. Specific examples of such networks may include wireless networks provided by the mobile terminal's communication provider. In one example, the communication device includes a network interface controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the communication device may be a radio frequency (RF) module used for wireless communication with the Internet.

[0047] The display device can be, for example, a touchscreen liquid crystal display (LCD) and a touch display (also referred to as a "touchscreen" or "touch screen"). This LCD allows users to interact with the user interface of the mobile terminal. In some embodiments, the mobile terminal has a graphical user interface (GUI), allowing users to interact with the GUI through finger contact and / or gestures on a touch-sensitive surface. Optional human-computer interaction functions include: video conferencing, instant messaging, sending and receiving emails, call interfaces, playing digital video, playing digital music, and / or web browsing, etc. Executable instructions for performing the above human-computer interaction functions are configured / stored in one or more processor-executable computer program products or readable storage media. This embodiment provides a fusion positioning method operating on an electronic device. Figure 1 This is a flowchart of a fusion positioning method according to one embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps:

[0048] Step S10: Obtain vehicle measurement and observation data;

[0049] The measurement data is obtained from the vehicle's gyroscope and wheel speedometer, while the observation data is obtained from various positioning sensors of the vehicle's positioning system.

[0050] The vehicle's measurement data is obtained directly from the vehicle's gyroscope and wheel speedometers. This data includes, but is not limited to, the vehicle's angular velocity and speed. The gyroscope measures the angular velocity, and the wheel speedometers measure the speed. The vehicle's observation data is obtained from various positioning sensors within the vehicle's positioning system. These sensors include, but are not limited to, LiDAR, GPS, cameras, and mapping equipment. The observation data obtained from different sensors may differ. For example, LiDAR positioning provides the vehicle's pose information, including its position and heading angle, while GPS positioning provides its three-dimensional coordinates, speed, and time information. The camera acquires information about the vehicle's surrounding environment to determine the distance between the vehicle and surrounding objects, thus locating the vehicle. Mapping equipment determines the vehicle's position to locate it.

[0051] It is understandable that, since multiple positioning sensors can obtain vehicle positioning information through different dimensions, the vehicle observation data obtained through multiple positioning sensors is multidimensional data.

[0052] Therefore, by acquiring vehicle measurement data through the vehicle's gyroscope and wheel speedometer, and by acquiring vehicle observation data through various positioning sensors of the vehicle positioning system, accurate measurement and observation data can be provided for the subsequent determination of the vehicle's first information and the updating of the second information, thereby ensuring the accuracy of the first information and the updated second information.

[0053] Step S11: Determine the first information of the vehicle based on the measurement data;

[0054] The first piece of information is used to update the vehicle's target information, which represents the vehicle's location information.

[0055] When locating a vehicle using the indirect Kalman filter algorithm (error Kalman filter algorithm), the vehicle's true state is decomposed into two forms: an integral state and an error state. The first information can be understood as the positioning information in the integral state, which is not affected by the uncertainty of the system and has no error.

[0056] By combining the vehicle's positioning information in the integration state and the error state, we can obtain the vehicle's positioning information in the real state, which is the target information. This target information can accurately represent the vehicle's position. Therefore, it can be understood that the vehicle's positioning information in the integration state can update the vehicle's positioning information in the real state.

[0057] Optionally, the first information includes first heading angle information, first position information, and first gyroscope zero-bias information. The first heading angle information is the vehicle's attitude information in the integral state, which can be represented by a rotation matrix, denoted as... The first position information is the vehicle's position information in the integral state, which can be represented by a three-dimensional spatial vector, denoted as . The first gyroscope zero-bias information is the zero-bias of the vehicle's gyroscope when measuring angular velocity in the integration state, denoted as...

[0058] Optionally, the vehicle angular velocity detected by the gyroscope in the measurement data is denoted as ω, and the vehicle speed detected by the wheel speed sensor is denoted as v. Substituting the measurement data into the first kinematic model of the vehicle in the integral state allows the calculation of the vehicle's first heading angle information in the integral state. and first location information This enables the calculation of the vehicle's position and attitude (i.e., the calculation of the vehicle's trajectory).

[0059] Alternatively, the first kinematic model of the vehicle in the integral state can be expressed by the following formulas (1)-(4):

[0060]

[0061]

[0062]

[0063] ω b =ω b +ωb ω (4)

[0064] Among them, in formula (1) This represents the vehicle's heading angle information at time t+1 under integral state. This represents the heading angle of the vehicle at time t in the integral state. Δt represents the time length between time t+1 and time t. It should be noted that time t+1 and time t simply represent two different times, and do not necessarily mean that the time length between time t+1 and time t is 1.

[0065] Understandably, due to the zero bias and noise of the vehicle's gyroscope, the equation (1)... This represents the vehicle's true angular velocity at time t, estimated using formulas (3) and (4). Specifically, the zero bias of the gyroscope is denoted as ω. b The noise of the gyroscope is denoted as ω. n ω n This can be Gaussian white noise for the gyroscope, with a mean of 0 and a standard deviation of σ. ωn Let ω be the Gaussian white noise of the gyroscope with zero bias. bω Its mean is 0 and its standard deviation is σ. ωω Therefore, the vehicle's true angular velocity at time t can be accurately estimated using formulas (3) and (4), thus accurately calculating the vehicle's pose.

[0066] In formula (1), exp is the calculation of the exponential function. For example, exp(A) refers to e raised to the power of A. This represents the result obtained after cross product mapping. The cross product matrix.

[0067] In formula (2) This represents the vehicle's position information at time t+1 under integral state. This represents the vehicle's position information at time t under integral state, v t This represents the vehicle speed detected by the wheel speed gauge at time t.

[0068] Therefore, by determining the first information of the vehicle based on the measurement data obtained by the vehicle gyroscope and wheel speedometer, accurate first information can be provided for the subsequent determination of the second information and the acquisition of the vehicle's target information, thereby improving the accuracy of the vehicle positioning information.

[0069] Step S12: Determine the vehicle's second information based on the first information and the corresponding relationship;

[0070] The correspondence relationship is used to represent the relationship between the first information, the second information, and the target information. The second information is used to update the measurement error of the vehicle positioning system.

[0071] Optionally, the correspondence can be found in Table 1 below. Table 1 shows the relationship between the vehicle's heading angle information, position information, and gyroscope zero-bias information in the real state, integral state, and error state, that is, the relationship between the vehicle's positioning information in the real state, integral state, and error state. It can be seen that when the vehicle is in the integral state...

[0072] By combining the positioning information from the error state with the positioning information from the error state, we can obtain the positioning information of the vehicle in the real state.

[0073] Table 1

[0074]

[0075]

[0076] The second piece of information can be understood as positioning information in an error state. This positioning information is affected by the system's uncertainty and therefore contains errors. It's understandable that since the vehicle's positioning information in its true state requires combining the positioning information from the integral state and the error state to obtain an accurate result, the positioning information in the error state can update the vehicle's positioning information in its true state. Specifically, because the positioning information in the error state is affected by the system's uncertainty and contains errors, it can be understood that the vehicle's positioning information in the error state can update the measurement error of the vehicle positioning system.

[0077] Optionally, the second information includes second heading angle information, second position information, and second gyroscope zero-bias information. The second heading angle information is the vehicle's attitude information under error conditions, denoted as δR. The second position information is the vehicle's position information under error conditions, denoted as δP. The second gyroscope zero-bias information is the zero-bias of the vehicle's gyroscope when measuring angular velocity under error conditions, denoted as δω. b .

[0078] Optionally, based on the first information and the correspondence, the second kinematic model of the vehicle's positioning information under the error state can be derived. The second kinematic model of the vehicle under the error state can be expressed by the following formula (5):

[0079]

[0080] In formula (5), I represents the identity matrix. and Let represent the state transition matrix, and σv represent the variance of the velocity. It can be seen that, based on the first information, the correspondence, and the above formula (5), the second information of the vehicle under the error state can be determined. Furthermore, this second information can be understood as the error obtained through estimation.

[0081] Therefore, based on the first information of the vehicle in the integral state and the corresponding relationship, the second information of the vehicle in the error state can be determined, thereby enabling the determination of the second information corresponding to the first information, providing an accurate data basis for merging the first information and the second information into the target information in the future.

[0082] Step S13: Fuse the observation data and the second information according to the fusion strategy;

[0083] The fusion strategy is used to update the second information, and the updated information is used to represent the updated second information.

[0084] Step S13 can be understood as fusing the observation data obtained from multiple positioning sensors of the vehicle positioning system with the second information determined based on the first information and the correspondence, according to the fusion strategy. The purpose of fusing the observation data and the second information is to update the second information. Since the vehicle positioning system has measurement errors, large errors can lead to inaccurate positioning information. Therefore, it is necessary to reduce the measurement errors of the vehicle positioning system by fusing observation data obtained from multiple positioning sensors, making the positioning information more accurate.

[0085] The observation data obtained from various positioning sensors in the vehicle positioning system is represented by y. Since the observation data is acquired through multiple positioning sensors, unavoidable observation errors will occur due to the inherent accuracy of the sensors themselves. This observation error is represented by V, which can be understood as representing the sensor's own observation error. The transformation function from the state of the vehicle positioning system to the observation space is represented by h(x). It can be understood that different positioning sensors obtain different observation data, therefore the specific form of the corresponding transformation function h(x) will differ.

[0086] Specifically, the mathematical expression for the observed data y is shown in formula (6):

[0087] y = h(x) + V(6)

[0088] Based on formula (6), the mathematical expression of the fusion strategy can be obtained. Specifically, the data expression of the fusion strategy is shown in formulas (7)-(9):

[0089] K = QH T (HQH T +V) -1 (7)

[0090]

[0091] Q = (1 - KH)Q (9)

[0092] Where Q represents the covariance matrix under the error state, H represents the Jacobian matrix of the transformation function h(x) with respect to the state, and K represents the Kalman gain of the indirect Kalman filter algorithm. This can be understood as the actual observation error obtained through actual observation using sensors, which is affected by both environmental factors and the accuracy of the sensors themselves.

[0093] Based on the above fusion strategy, the observation data and the second information are fused. This can be understood as substituting formulas (5) and (6) into formulas (7)-(9) to obtain the updated information, i.e., the updated second information. The updated information can be expressed as follows:

[0094] By fusing observation data from multiple sensors with second information under error conditions and continuously updating the second information, the error of the second information under error conditions becomes smaller and smaller, thereby improving the accuracy of the positioning information in the real state obtained by merging the first information and the second information, making the positioning result more accurate.

[0095] Step S14: Merge the first information with the updated information to obtain the target information.

[0096] The first information in the integral state and the updated information (i.e., the second information in the updated error state) are combined according to the combination form given in Table 1 to obtain the target information used to represent the vehicle positioning information in the real state. Since the updated information can be obtained by fusing observation data from multiple positioning sensors, the error of the updated information is extremely small. The target information obtained by combining the first information and the updated information has extremely high accuracy, thereby improving the accuracy of the vehicle positioning system.

[0097] Figure 2 This is a schematic diagram of the overall system architecture of the fusion positioning method according to one embodiment of the present invention, such as... Figure 2The implementation process of steps S10 to S14 above is comprehensively explained as shown. The system includes three modules: a trajectory calculation module, a measurement update module, and a positioning result module. The trajectory calculation module is used to determine the vehicle's positioning information in the integration state, i.e., the first information. The measurement update module is used to determine the vehicle's positioning information in the error state, i.e., the second information, and updates the second information based on observation data obtained from multiple positioning sensors to obtain updated information. The positioning result module is used to merge the first information determined by the trajectory calculation module and the updated information determined by the measurement update module to obtain the vehicle's positioning information in the real state, i.e., the target information.

[0098] Optionally, the trajectory calculation module performs integration calculations based on the vehicle's angular velocity obtained from the IMU gyroscope and the vehicle's speed obtained from the wheel speedometer to obtain the first information of the vehicle in the integrated state. The measurement update module determines the second information of the vehicle in the error state based on the first information and the corresponding relationship, and updates the second information through various positioning sensors (such as LiDAR, GPS, camera, and map equipment) to obtain the updated second information, i.e., the updated information. Finally, the positioning result module merges the first information and the updated information to obtain the target information of the vehicle in the real state, i.e., the high-precision positioning result.

[0099] Through the above steps, measurement data is obtained from the vehicle's gyroscope and wheel speedometer, as well as observation data from multiple positioning sensors in the vehicle positioning system. First information for updating the vehicle's positioning information is determined based on the measurement data. Second information for updating the measurement error of the vehicle positioning system is then determined based on the first information and a corresponding relationship, where the correspondence represents the relationship between the first information, the second information, and the target information (vehicle positioning information). The observation data and the second information are then fused according to a fusion strategy to obtain updated information, where the fusion strategy updates the second information, and the updated information represents the updated second information. Finally, the first information and the updated information are merged to obtain the target information (vehicle positioning information). This achieves the goal of high-precision vehicle positioning by fusing data from multiple positioning sensors. The method is robust and has a low implementation cost. Furthermore, the method is not limited by special scenarios, avoiding inaccurate vehicle positioning results in special environments, thus improving vehicle positioning accuracy and solving the technical problem of low positioning accuracy caused by using a single positioning method in related technologies.

[0100] Alternatively, a variety of positioning sensors may be used, including lidar, GPS, photographic equipment, and mapping equipment.

[0101] The vehicle's observation data is obtained by using various positioning sensors of the vehicle positioning system. These positioning sensors include, but are not limited to, LiDAR, GPS, camera, and map devices. For details, please refer to the description of step S10 above, which will not be elaborated here.

[0102] Therefore, by acquiring vehicle observation data from various positioning sensors in the vehicle positioning system, it is possible to obtain various types of observation information from multiple perspectives and in a comprehensive manner, thereby ensuring the accuracy of subsequent positioning results.

[0103] Optionally, in step S10, acquiring the vehicle's measurement data may include the following steps:

[0104] Step S100: Obtain the angular velocity of the vehicle based on the gyroscope;

[0105] The angular velocity information of the vehicle is obtained by detecting the angular velocity signal of the vehicle relative to the navigation coordinate system using the gyroscope. For details, please refer to the description of step S10 above, which will not be elaborated here.

[0106] It is understandable that, since gyroscopes have fixed-axis and precession properties, and axles have a force that keeps them level, the faster the wheels spin, the less likely they are to fall over. Therefore, obtaining the vehicle's angular velocity through a gyroscope has high stability and can provide accurate vehicle angular velocity ω for subsequent determination of the vehicle's initial information.

[0107] Furthermore, since the IMU's gyroscope has zero bias and noise, it may affect the final acquired vehicle angular velocity ω. Therefore, the Gaussian white noise of the gyroscope's zero bias is represented as ω. bω Its mean is 0 and its standard deviation is σ. ωω The zero bias ω of the gyroscope can be calculated using the above formula (4). b The Gaussian white noise of a gyroscope is represented by ω. n Its mean is 0 and its standard deviation is σ. ωn Then the estimated true vehicle angular velocity It can be calculated by the above formula (3), thereby ensuring the accuracy of the vehicle's first information. Specifically, please refer to the description of the above step S10, which will not be elaborated here.

[0108] Step S101: Obtain the vehicle speed based on the wheel speed meter.

[0109] The vehicle speed is obtained by measuring the rotational speed of the vehicle's wheels using a wheel speed sensor. Generally speaking, any speed sensor can be used as a wheel speed sensor. However, considering practical factors such as the working environment of the wheel and the size of the space, the commonly used wheel speed sensors are mainly: magnetoelectric wheel speed sensors and Hall effect wheel speed sensors.

[0110] In one alternative example, a magnetoelectric wheel speed sensor can be selected as the wheel speed gauge to obtain the vehicle speed v. The magnetoelectric wheel speed sensor consists of a permanent magnetic core and a coil. Magnetic lines of force emerge from one pole of the core, pass through a toothed ring and air, and return to the other pole. Since the sensor's coil is wound around the magnetic core, these magnetic lines of force also pass through the coil. When the wheel rotates, the toothed ring (rotor) rotates synchronously with the wheel. The teeth and gaps on the toothed ring pass rapidly through the sensor's magnetic field, resulting in a change in the magnetic reluctance of the magnetic circuit. This causes a change in the induced electromotive force in the coil, generating potential pulses of a certain amplitude and frequency. The frequency of these pulses, i.e., the number of pulses generated per second, reflects the speed of the wheel's rotation, thus yielding the vehicle speed v.

[0111] In another alternative example, a Hall effect wheel speed sensor can be selected as the wheel speed gauge to obtain the vehicle speed v. The Hall effect wheel speed sensor utilizes the Hall effect principle. When using a Hall element as a wheel speed sensor for a car, magnetic flux density B is often used as the input signal. The change in magnetic flux density B with wheel speed generates Hall potential pulses. After amplification, shaping, and power amplification within the Hall integrated circuit, a pulse sequence is output. The idle percentage of this sequence varies with the angular velocity of the turntable. The rotation of the toothed disc alternately changes the magnetic reluctance, causing changes in magnetic flux density, which allows the measurement of the Hall potential pulses output by the sensor. The frequency of the pulses, i.e., the number of pulses generated per second, reflects the speed of wheel rotation. The wheel speed, i.e., the vehicle speed v, can be obtained from the pulse frequency.

[0112] Optionally, in step S11, determining the first information of the vehicle based on the measurement data may include the following execution steps:

[0113] Step S110: Integrate the angular velocity and velocity to obtain the first information.

[0114] The estimated true vehicle angular velocity obtained through the gyroscope The vehicle speed v obtained by the wheel speed meter is integrated according to the above formulas (1)-(4) to obtain the first information in the integrated state, including the three-dimensional attitude of the vehicle during rotation, i.e., the first heading angle information. And the vehicle's position in three-dimensional space, i.e., the first position information. This allows for the calculation of the vehicle's position and orientation (i.e., trajectory calculation). For details, please refer to the description of step S11 above, which will not be elaborated upon here.

[0115] Since this embodiment of the invention uses an error Kalman filter-based method to fuse positioning data results from multiple sensors, this method is an indirect Kalman filter algorithm. The true state is decomposed into two forms: an integral state and an error state. The first information in the integral state is used as the result of vehicle trajectory estimation, and then the estimated true vehicle angular velocity generated at different times is substituted into the equation. The vehicle obtains different first information from the vehicle speed v, thereby updating the vehicle state. When merging the first information with the updated information in the future, it can provide real-time and accurate first information, thus ensuring the accuracy of the target information.

[0116] Optionally, in step S13, fusing the observation data and the second information according to the fusion strategy to obtain the updated information may include the following execution steps:

[0117] Step S130: Fuse the first observation data and the second information according to the fusion strategy to obtain the first update information;

[0118] Step S131: Fuse the second observation data and the first update information according to the fusion strategy to obtain the second update information.

[0119] The first observation data is the data obtained from the observation of the first positioning sensor, and the second observation data is the data obtained from the observation of the second positioning sensor. The multiple positioning sensors include the first positioning sensor and the second positioning sensor.

[0120] It is understood that the observation data is obtained by various positioning sensors of the vehicle positioning system observing the vehicle. These various positioning sensors include, but are not limited to, LiDAR, GPS, cameras, and mapping devices. The aforementioned first positioning sensor and second positioning sensor simply represent different positioning sensors and are not specifically limited to any particular type of positioning sensor. Correspondingly, the first observation data and the second observation data are observation data corresponding to the first positioning sensor and the second positioning sensor, and are not specifically limited to any particular type of observation data.

[0121] For example, taking the fusion update using two positioning sensors, A and B, where the first observation data is obtained from the observation of positioning sensor A and the second observation data is obtained from the observation of positioning sensor B, when fusing the observation data and the second information according to the fusion strategy, the observation data (e.g., the first observation data) obtained by one positioning sensor (e.g., positioning sensor A) is first fused with the second information to obtain the first update information. Then, the observation data (e.g., the second observation data) obtained by the other positioning sensor (e.g., positioning sensor B) is fused with the first update information to obtain the second update information. Since only two positioning sensors are involved here, the second update information is the target update information, which is also the update information in step S13.

[0122] Optionally, the vehicle positioning system may include multiple positioning sensors, so the observation data obtained from multiple positioning sensors can be fused. The above example of fusion and updating using two positioning sensors is merely an example and is not limited to fusion of observation data obtained from only two positioning sensors.

[0123] For example, a LiDAR (Light Detection and Ranging) sensor can be used as the first positioning sensor, and the observation data obtained through the LiDAR sensor is the first observation data. A Global Positioning System (GPS) sensor can be used as the second positioning sensor, and the observation data obtained through the GPS sensor is the second observation data.

[0124] Optionally, the lidar acquires the first observation data through a point cloud matching module. The point cloud matching module extracts features from the real-time point cloud data input by the lidar sensor driver module and matches the extracted feature point cloud with a pre-collected point cloud map to obtain an accurate matching and positioning result.

[0125] Figure 3 This is a structural block diagram of a lidar point cloud matching module according to one embodiment of the present invention, such as... Figure 3As shown, the sensor driving module acquires real-time point cloud data, vehicle body signals, and IMU signals, and transmits the real-time point cloud to the feature extraction module. The feature extraction module uses a feature extraction algorithm to lightweight the real-time point cloud, obtaining a feature point cloud, which is then transmitted to the odometer module and the matching and positioning module. The sensor driving module also transmits the vehicle body signals and IMU signals to the odometer module. The odometer module receives the vehicle body signals and IMU signals transmitted from the sensor driving module, as well as the feature point cloud transmitted from the feature extraction module. It uses an inter-frame matching algorithm to obtain the relative motion between adjacent point cloud frames, thus providing the matching and positioning module with initial matching values ​​for the vehicle's attitude. The initial matching values ​​are transmitted to the point cloud map module, which matches a point cloud map within a certain range based on the initial matching values, providing the matching and positioning module with a map point cloud. The matching and positioning module receives the feature point cloud transmitted from the feature extraction module and the map point cloud transmitted from the point cloud map module, thereby obtaining the vehicle's pose transformation, i.e., determining the vehicle's position.

[0126] Understandably, during the operation of autonomous vehicles, dynamic obstacles may appear and affect the matching and localization results. Therefore, the matching and localization module adopts the Normal Distribution Transform (NDT) algorithm as the point cloud registration algorithm to improve the stability of the point cloud matching and localization algorithm. The matching and localization module registers the feature point cloud with the map point cloud through the NDT algorithm, thereby obtaining the optimized vehicle accurate pose transformation result.

[0127] The matching and positioning module outputs the vehicle's matched attitude information RL and matched position information PL. The errors generated by the matched attitude information RL and matched position information PL during actual observation are expressed by formulas (10) and (11), where eR represents the error of the matched attitude information RL and eP represents the error of the matched position information PL. Formulas (10) and (11) are the actual observation errors generated during the observation process. Formulas (10) and (11) are expressed as follows:

[0128]

[0129]

[0130] The Jacobian matrix H of the transformation function h(x) obtained from lidar observations is expressed by formula (12), where J1 represents the Jacobian matrix. Formula (12) is as follows:

[0131]

[0132] Optionally, by substituting formulas (10)-(12) into formulas (7)-(9), the first updated information obtained by fusing the first observation data with the second information can be obtained.

[0133] Furthermore, since traditional mechanical lidar is expensive, embodiments of this invention can use solid-state lidar for real-time point cloud data acquisition. For example, emerging technologies such as optical phased arrays, photonic integrated circuits, and far-field radiation patterns can be used to replace mechanical rotating parts to achieve adjustment of the emitted laser angle.

[0134] According to the fusion strategy, the second information and the first observation data obtained by the first positioning sensor are fused to obtain the first update information. In this way, when the second observation data and the first update information are fused to obtain the second update information, the first update information can be provided accurately, thereby ensuring the accuracy of the second update information.

[0135] Accordingly, the Global Positioning System (GPS) can be used as a second positioning sensor. The GPS antenna built into the vehicle will receive data from at least 3 of the 24 GPS satellites orbiting the Earth, thereby determining the current position of the vehicle. The navigation host matches the position coordinates determined by the GPS satellite signals with the electronic map data, thereby determining the accurate position information of the vehicle in the electronic map. In other words, the observation data obtained by the Global Positioning System (GPS) can be used as the second observation data.

[0136] According to the fusion strategy, the first update information is fused with the second observation data obtained by the second positioning sensor to obtain the second update information. This allows for the provision of accurate second update information when the first information and the second update information are subsequently merged to obtain the target information, thereby ensuring the accuracy of the target information.

[0137] It is understood that the above only illustrates the process of fusing and updating the first observation data obtained from the first positioning sensor with the second observation data obtained from the second positioning sensor. Alternatively, a camera can be used as a third positioning sensor to obtain third observation data, and a map device can be used as a fourth positioning sensor to obtain fourth observation data. The second update information is then further fused and updated using the third and fourth observation data, with the update process similar to the above description, and will not be repeated here, thus minimizing the error in the obtained update information.

[0138] The fusion strategy combines the first observation data and the second information to obtain the first updated information, and the fusion strategy also combines the second observation data and the first updated information to obtain the second updated information. Essentially, both are updating the second information. By continuously fusing observation data obtained from different positioning sensors, the second information under error conditions is updated. This ensures that when the first information and the updated information are subsequently merged to obtain the target information, the updated information is the second information after fusing the observation data from various positioning sensors, thereby minimizing the impact of various errors on the target information.

[0139] Optionally, in step S131, after fusing the second observation data and the first update information according to the fusion strategy to obtain the second update information, the following execution steps may be included:

[0140] Step S132: Merge the first information with the second updated information to obtain the target information.

[0141] The second update information obtained by fusing observation data from multiple positioning sensors is combined with the first information in the integral state. The merging process refers to the combination form given in Table 1 above, so as to obtain the target information in the real state, that is, the vehicle's positioning information. This ensures that the target information always goes through two stages: trajectory calculation and measurement update. Furthermore, by fusing observation data from multiple positioning sensors, the positioning error is effectively reduced, thereby ensuring the accuracy of the vehicle's positioning information.

[0142] Therefore, it can be seen that the fusion positioning method proposed in this embodiment of the invention can calculate vehicle trajectory based on the mathematical model of IUM and wheel speed gauge components, resulting in stable calculation results that are easy to implement. Furthermore, this embodiment of the invention proposes a method based on error Kalman filtering to fuse positioning data results from multiple sensors, enabling error state updates and making the positioning results more accurate.

[0143] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0144] This embodiment also provides a fusion positioning device for implementing the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, hardware implementations, or a combination of software and hardware, are also possible and contemplated.

[0145] Figure 4 This is a structural block diagram of a fusion positioning device according to one embodiment of the present invention, such as... Figure 4 As shown, a fusion positioning device 400 is used as an example. This device includes: an acquisition module 401, which is used to acquire measurement data and observation data of a vehicle, wherein the measurement data is data obtained from the vehicle's gyroscope and wheel speedometer, and the observation data is data observed from multiple positioning sensors of the vehicle positioning system; a determination module 402, which is used to determine first information of the vehicle based on the measurement data, wherein the first information is used to update the vehicle's target information, and the target information is used to represent the vehicle's positioning information; the determination module 402 is also used to determine second information of the vehicle based on the first information and a correspondence, wherein the correspondence is used to represent the relationship between the first information, the second information, and the target information, and the second information is used to update the measurement error of the vehicle positioning system; a fusion module 403, which is used to fuse the observation data and the second information according to a fusion strategy to obtain updated information, wherein the fusion strategy 403 is also used to update the second information, and the updated information is used to represent the updated second information; and a merging module 404, which is used to merge the first information and the updated information to obtain target information.

[0146] Optionally, the acquisition module 401 is also used to acquire the angular velocity of the vehicle based on the gyroscope and the speed of the vehicle based on the wheel speed meter.

[0147] Optionally, the determining module 402 is also used to integrate the angular velocity and velocity to obtain the first information.

[0148] Optionally, the fusion module 403 is further configured to fuse the first observation data and the second information according to the fusion strategy to obtain the first update information, wherein the first observation data is data observed by the first positioning sensor; and to fuse the second observation data and the first update information according to the fusion strategy to obtain the second update information, wherein the second observation data is data observed by the second positioning sensor, and the multiple positioning sensors include the first positioning sensor and the second positioning sensor.

[0149] Optionally, the merging module 404 is also used to merge the first information with the second updated information to obtain the target information.

[0150] Alternatively, a variety of positioning sensors may be used, including lidar, GPS, photographic equipment, and mapping equipment.

[0151] It should be noted that the above modules can be implemented by software or hardware. For the latter, they can be implemented in the following ways, but are not limited to: all the above modules are located in the same processor; or, the above modules are located in different processors in any combination.

[0152] According to one embodiment of the present invention, a processor is also provided, the processor being used to run a program, wherein the program is configured to execute the fusion positioning method of any of the above-mentioned methods during runtime.

[0153] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:

[0154] Step S1: Obtain vehicle measurement and observation data;

[0155] Step S2: Determine the vehicle's first information based on the measurement data;

[0156] Step S3: Determine the vehicle's second information based on the first information and the corresponding relationship;

[0157] Step S4: Fuse the observation data and the second information according to the fusion strategy;

[0158] Step S5: Merge the first information with the updated information to obtain the target information.

[0159] Embodiments of the present invention also provide a computer-readable storage medium storing a computer program, wherein the computer program is configured to perform the steps in any of the above method embodiments when run on a computer or processor.

[0160] Optionally, in this embodiment, the computer-readable storage medium may be configured to store a computer program for performing the following steps:

[0161] Step S1: Obtain vehicle measurement and observation data;

[0162] Step S2: Determine the vehicle's first information based on the measurement data;

[0163] Step S3: Determine the vehicle's second information based on the first information and the corresponding relationship;

[0164] Step S4: Fuse the observation data and the second information according to the fusion strategy;

[0165] Step S5: Merge the first information with the updated information to obtain the target information.

[0166] Optionally, in this embodiment, the computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0167] Embodiments of the present invention also provide an electronic device including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.

[0168] Optionally, in this embodiment, the processor in the above-described electronic device may be configured to run a computer program to perform the following steps:

[0169] Step S1: Obtain vehicle measurement and observation data;

[0170] Step S2: Determine the vehicle's first information based on the measurement data;

[0171] Step S3: Determine the vehicle's second information based on the first information and the corresponding relationship;

[0172] Step S4: Fuse the observation data and the second information according to the fusion strategy;

[0173] Step S5: Merge the first information with the updated information to obtain the target information.

[0174] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated here.

[0175] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0176] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0177] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0178] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0179] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0180] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0181] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A fusion positioning method, characterized by, The method comprises: obtaining measurement data and observation data of a vehicle, wherein the measurement data is data measured according to a gyroscope and a tachometer of the vehicle, and the observation data is data observed according to a plurality of positioning sensors of a vehicle positioning system; determining first information of the vehicle according to the measurement data, wherein the first information is used to update target information of the vehicle, and the target information is used to represent positioning information of the vehicle; determining second information of the vehicle according to the first information and a corresponding relationship, wherein the corresponding relationship is used to represent a relationship among the first information, the second information and the target information, and the second information is used to update a measurement error of the vehicle positioning system; fusing the observation data and the second information according to a fusion strategy to obtain update information, wherein the fusion strategy is used to update the second information, and the update information is used to represent the updated second information; merging the first information and the update information to obtain the target information; wherein the fusing the observation data and the second information according to the fusion strategy to obtain the update information comprises: fusing first observation data and the second information according to the fusion strategy to obtain first update information, wherein the first observation data is data observed according to a first positioning sensor; and fusing second observation data and the first update information according to the fusion strategy to obtain second update information, wherein the second observation data is data observed according to a second positioning sensor, and the plurality of positioning sensors comprise the first positioning sensor and the second positioning sensor.

2. The method of claim 1, wherein, The merging the first information and the update information to obtain the target information comprises: merging the first information and the second update information to obtain the target information.

3. The method according to any one of claims 1-2, characterized in that, The obtaining the measurement data of the vehicle comprises: obtaining an angular velocity of the vehicle according to the gyroscope; obtaining a speed of the vehicle according to the tachometer.

4. The method of claim 3, wherein, The determining the first information of the vehicle according to the measurement data comprises: integrating the angular velocity and the speed to obtain the first information.

5. The method according to any one of claims 1-2, characterized in that, The plurality of positioning sensors comprise a laser radar, a global positioning system, a photographic device and a map device.

6. A fusion positioning device, characterized by The method comprises: an obtaining module, configured to obtain measurement data and observation data of a vehicle, wherein the measurement data is data measured according to a gyroscope and a tachometer of the vehicle, and the observation data is data observed according to a plurality of positioning sensors of a vehicle positioning system; a determining module, configured to determine first information of the vehicle according to the measurement data, wherein the first information is used to update target information of the vehicle, and the target information is used to represent positioning information of the vehicle; the determining module is further configured to determine second information of the vehicle according to the first information and a corresponding relationship, wherein the corresponding relationship is used to represent a relationship among the first information, the second information and the target information, and the second information is used to update a measurement error of the vehicle positioning system; a fusion module, configured to fuse the observation data and the second information according to a fusion strategy to obtain updated information, wherein the fusion strategy is used to update the second information, and the updated information is used to represent the updated second information; a merging module, configured to merge the first information and the updated information to obtain the target information; the fusion module is further configured to fuse first observation data and the second information according to the fusion strategy to obtain first updated information, wherein the first observation data is obtained according to a first positioning sensor; and fuse second observation data and the first updated information according to the fusion strategy to obtain second updated information, wherein the second observation data is obtained according to a second positioning sensor, and the plurality of positioning sensors include the first positioning sensor and the second positioning sensor.

7. A processor, comprising: the processor is configured to run a program, wherein the program is set to execute the fusion positioning method in any one of claims 1 to 5 when running on the processor.

8. A computer-readable storage medium, characterized in that, the computer readable storage medium stores a computer program, wherein the computer program is set to execute the fusion positioning method in any one of claims 1 to 5 when running on the computer or the processor. 9.An electronic device comprising a memory and a processor, the electronic device characterized by, the memory stores a computer program, and the processor is set to run the computer program to execute the fusion positioning method in any one of claims 1 to 5.

Images