Pose deviation determination method, device, equipment, storage medium and product

Abstract

The application discloses a pose deviation determination method and device, equipment, a storage medium and a product, and belongs to the computer technical field. The method comprises the following steps: acquiring target acceleration data corresponding to a motion sensor in real time under the condition that a target carrier is in a stationary state; determining turning information corresponding to a sensor coordinate system based on the target acceleration data; and determining pose deviation information corresponding to the target sensor according to the turning information. The embodiments of the application can be applied to various fields such as the map field, the traffic field, the vehicle-mounted scene and the like. Through real-time acquisition of acceleration data corresponding to the motion sensor under the condition that the carrier is in the stationary state, the turning information capable of representing the position transformation relationship between the sensor coordinate system and the carrier coordinate system can be determined, so that the pose deviation information corresponding to the current installation deviation angle of the motion sensor can be determined according to the turning information, and the pose deviation information determination efficiency and accuracy are improved.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method, apparatus, device, storage medium and product for determining pose deviation. Background Technology

[0002] With the development of computer technology, motion sensors are increasingly widely used in various fields. In practical applications, due to installation errors, there is an angular deviation between the motion sensor and its corresponding carrier.

[0003] In related technologies, motion sensors are typically placed on a carrier to perform a preset motion. During this motion, the motion sensor collects angular velocity and acceleration data. The device can then perform complementary filtering or Kalman filtering algorithms based on the angular velocity and acceleration data to calculate the installation deviation angle between the motion sensor and its corresponding carrier in real time.

[0004] In related technologies, determining the aforementioned installation deviation angle involves a large amount of calculation and is inefficient. Summary of the Invention

[0005] This application provides a method, apparatus, device, storage medium, and product for determining pose deviation, which can reduce the computational load for determining pose deviation information and improve the efficiency and accuracy of pose deviation information determination.

[0006] According to one aspect of the embodiments of this application, a method for determining pose deviation is provided, the method comprising:

[0007] When the target carrier is stationary, the target acceleration data corresponding to the motion sensor is acquired in real time. The motion sensor is installed on the vehicle-mounted equipment, and the vehicle-mounted equipment is installed on the target carrier. The target acceleration data is used to characterize the force information of the motion sensor.

[0008] Based on the target acceleration data, the steering information corresponding to the sensor coordinate system is determined. The sensor coordinate system is the coordinate system corresponding to the motion sensor. The steering information is used to characterize the position transformation relationship between the sensor coordinate system and the carrier coordinate system corresponding to the target carrier.

[0009] Based on the steering information, the pose deviation information corresponding to the target sensor is determined, and the pose deviation information is used to characterize the installation deviation angle of the motion sensor.

[0010] According to one aspect of the embodiments of this application, a pose deviation determination device is provided, the device comprising:

[0011] An acceleration data acquisition module is used to acquire target acceleration data corresponding to a motion sensor in real time when the target carrier is stationary. The motion sensor is installed on an in-vehicle device, and the in-vehicle device is installed on the target carrier. The target acceleration data is used to characterize the force information of the motion sensor.

[0012] The steering information determination module is used to determine the steering information corresponding to the sensor coordinate system based on the target acceleration data. The sensor coordinate system is the coordinate system corresponding to the motion sensor. The steering information is used to characterize the position transformation relationship between the sensor coordinate system and the carrier coordinate system corresponding to the target carrier.

[0013] The pose deviation determination module is used to determine the pose deviation information corresponding to the target sensor based on the steering information. The pose deviation information is used to characterize the installation deviation angle of the motion sensor.

[0014] According to one aspect of the embodiments of this application, a computer device is provided, the computer device including a processor and a memory, the memory storing at least one instruction, at least one program, code set or instruction set, the at least one instruction, the at least one program, the code set or instruction set being loaded and executed by the processor to implement the above-described pose deviation determination method.

[0015] According to one aspect of the embodiments of this application, a vehicle-mounted device is provided, the vehicle-mounted device is equipped with a motion sensor, the target carrier corresponding to the vehicle-mounted device includes a vehicle, and the installation deviation angle between the motion sensor and the vehicle is determined by the above-described pose deviation determination method.

[0016] According to one aspect of the embodiments of this application, a computer-readable storage medium is provided, wherein at least one instruction, at least one program, code set, or instruction set is stored in the storage medium, and the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by a processor to implement the above-described pose deviation determination method.

[0017] According to one aspect of the embodiments of this application, a computer program product is provided, the computer program product including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, causing the computer device to perform to implement the above-described pose deviation determination method.

[0018] The technical solution provided in this application can bring the following beneficial effects:

[0019] By acquiring the acceleration data of the motion sensor in real time when the carrier is stationary, the steering information that characterizes the positional transformation relationship between the sensor coordinate system and the carrier coordinate system can be determined. Thus, the pose deviation information corresponding to the current installation deviation angle of the motion sensor can be determined based on the steering information, which reduces the amount of calculation required to determine the pose deviation information and improves the efficiency and accuracy of the pose deviation information determination. Attached Figure Description

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

[0021] Figure 1 This is a schematic diagram of an application runtime environment provided in one embodiment of this application;

[0022] Figure 2 This is a flowchart of a pose deviation determination method provided in one embodiment of this application. Figure 1 ;

[0023] Figure 3 This is a flowchart of a pose deviation determination method provided in one embodiment of this application. Figure 2 ;

[0024] Figure 4 An example illustration shows a real-view navigation page. Figure 1 ;

[0025] Figure 5 This is a flowchart of a pose deviation determination method provided in one embodiment of this application. Figure 3 ;

[0026] Figure 6 An exemplary flowchart illustrating the process of determining the angle vector is shown.

[0027] Figure 7 An example illustration shows a real-view navigation page. Figure 2 ;

[0028] Figure 8 This is a block diagram of a pose deviation determination device provided in one embodiment of this application;

[0029] Figure 9 This is a structural block diagram of a computer device provided in one embodiment of this application. Detailed Implementation

[0030] The embodiments of this application can be applied to various fields and scenarios, including but not limited to cloud technology, artificial intelligence, smart transportation, assisted driving, and vehicle scenarios. Before introducing the method embodiments provided in this application, a brief introduction will be given to the application fields, application scenarios, related terms or nouns that may be involved in the method embodiments of this application, so as to facilitate understanding by those skilled in the art.

[0031] Intelligent Traffic Systems (ITS), also known as Intelligent Transportation Systems, effectively integrate advanced science and technology (information technology, computer technology, data communication technology, sensor technology, electronic control technology, automatic control theory, operations research, artificial intelligence, etc.) into transportation, service control, and vehicle manufacturing. This strengthens the connection between vehicles, roads, and users, thereby forming a comprehensive transportation system that ensures safety, improves efficiency, enhances the environment, and saves energy.

[0032] Intelligent Vehicle Infrastructure Cooperative Systems (IVICS) are a development direction of Intelligent Transportation Systems (ITS). IVICS utilizes advanced wireless communication and next-generation Internet technologies to implement comprehensive, real-time dynamic information exchange between vehicles and infrastructure. Based on the collection and fusion of dynamic traffic information across all times and spaces, it conducts active vehicle safety control and cooperative road management, fully realizing effective collaboration between people, vehicles, and roads. This ensures traffic safety, improves traffic efficiency, and ultimately forms a safe, efficient, and environmentally friendly road traffic system.

[0033] An inertial measurement unit (IMU) mainly consists of a three-axis accelerometer and a three-axis gyroscope sensor.

[0034] Installation deviation angle: The initial angle formed by the sensor coordinate system and the carrier coordinate system of a motion sensor. For example, the angle formed between the inertial measurement unit inside the vehicle and the vehicle body coordinate system.

[0035] Online calibration: Unlike offline calibration methods that use recorded data to calibrate parameters, online calibration uses real-time data to calibrate installation deviation angles, making it more widely applicable.

[0036] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0037] Please refer to Figure 1This diagram illustrates an application runtime environment provided in one embodiment of this application. The application runtime environment may include: terminal 10 and server 20.

[0038] Terminal 10 includes, but is not limited to, electronic devices such as mobile phones, computers, smart voice interaction devices, smart home appliances, in-vehicle terminals, aircraft, game consoles, e-book readers, multimedia playback devices, and wearable devices. Application clients can be installed on terminal 10.

[0039] In this embodiment, the application described above can be any application capable of processing motion sensor data. Typically, this application is a map application. Of course, other types of applications besides map applications can also process motion sensor data. Examples include video applications, news applications, social applications, interactive entertainment applications, browser applications, shopping applications, content sharing applications, virtual reality (VR) applications, and augmented reality (AR) applications; this embodiment does not limit the specific application to these. Optionally, the application supports real-view navigation. Optionally, the terminal 10 runs a client version of the application. Optionally, the target carrier corresponding to the motion sensor includes the terminal 10 and the carrier corresponding to the terminal 10. The target carrier includes, but is not limited to, vehicles, ships, and aircraft.

[0040] Server 20 provides background services to clients of applications in terminal 10. For example, server 20 can be a background server for the aforementioned applications. Server 20 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. Optionally, server 20 can simultaneously provide background services to applications in multiple terminals 10.

[0041] Optionally, terminal 10 and server 20 can communicate with each other via network 30. Terminal 10 and server 20 can be directly or indirectly connected via wired or wireless communication, which is not limited herein.

[0042] Please refer to Figure 2 It illustrates the flowchart of a pose deviation determination method provided in one embodiment of this application. Figure 1This method can be applied to computer devices, which refer to electronic devices with data computing and processing capabilities. For example, the entity executing each step can be... Figure 1 Terminal 10 in the application runtime environment shown. The method may include the following steps (210-230).

[0043] Step 210: When the target carrier is stationary, acquire the target acceleration data corresponding to the motion sensor in real time.

[0044] Optionally, the aforementioned target acceleration data is used to characterize the force information of the motion sensor. An object's acceleration is directly proportional to the magnitude of the net force acting on it and inversely proportional to its mass; its direction is the same as the direction of the net force. Therefore, the aforementioned target acceleration data can be used to characterize the force information of the motion sensor. When the motion sensor is stationary, the force information can be gravity information.

[0045] Optionally, the motion sensor is mounted on the target carrier. Alternatively, the motion sensor is mounted on an in-vehicle device, which in turn is mounted on the target carrier. The target carrier is the carrier corresponding to the motion sensor, and the bearing relationship between the target carrier and the motion sensor can be a direct bearing relationship or an indirect bearing relationship. For example, if the motion sensor is mounted in a terminal, and the terminal can be an in-vehicle device, which can be installed in a vehicle, then the vehicle can also be the target carrier corresponding to the motion sensor.

[0046] Optionally, the above-described position deviation method is applied to a terminal equipped with the aforementioned motion sensor, and the target carrier includes, but is not limited to, the terminal and its corresponding carrier. Optionally, the target terminal and the motion sensor have the same motion state; when the target carrier is stationary, the motion sensor is also stationary. Further, the stationary state is a horizontal stationary state. When the target carrier is in a horizontal stationary state, its corresponding carrier coordinate system is aligned with the direction of the gravity coordinate system.

[0047] Furthermore, the installation connection state between the target carrier and the motion sensor can be detached. Even if the motion sensor is detached from the target carrier, the installation deviation angle between the motion sensor detached from the target carrier and the target carrier in a stationary state can be determined by executing the technical solution provided in the embodiments of this application.

[0048] Optionally, the aforementioned terminals include in-vehicle terminals, such as in-vehicle infotainment systems. In-vehicle infotainment systems refer to terminals installed inside vehicles that provide human-machine interaction, navigation, entertainment, and other functions.

[0049] Optionally, the motion sensor mentioned above includes, but is not limited to, any sensor capable of acquiring acceleration data, such as an inertial measurement unit or an accelerometer. This application does not limit the degrees of freedom for the acceleration data acquired by the motion sensor.

[0050] In an exemplary embodiment, step 210 can be initiated and executed under various circumstances to determine the installation deviation angle of the motion sensor. For example, in a vehicle AR navigation scenario, each vehicle model has a fixed installation angle for the in-vehicle terminal, and in most cases, the in-vehicle terminal is located inside the vehicle. The in-vehicle terminal can be fixedly installed on the vehicle, or it can be non-fixedly installed on the vehicle but maintain a fixed positional relationship with the vehicle while driving, such as through a phone holder. In some usage scenarios, the position of the in-vehicle terminal and the vehicle may change. For example, during the development and debugging phase, the in-vehicle terminal may be removed separately and placed outside the vehicle for external debugging, and then reinstalled on the vehicle after debugging. Alternatively, if a user places a mobile terminal as an in-vehicle terminal inside the vehicle for navigation, there will be frequent positional changes. Due to the existence of installation errors, the installation deviation angle corresponding to the in-vehicle terminal will change, resulting in navigation positioning deviation and jitter in the AR navigation paving rendering effect, which greatly affects the positioning accuracy and the stability of AR navigation. Therefore, it is necessary to redetermine the installation deviation angle of the motion sensor. If offline acceleration data is used for offline calibration of the installation deviation angle, the determined installation deviation angle is not applicable to the current installation deviation angle. Therefore, in this embodiment, the target acceleration data corresponding to the motion sensor is obtained in real time to determine the installation deviation angle, which enables online calibration of the installation deviation angle.

[0051] In one possible implementation, such as Figure 3 As shown, before performing step 210 above, the following steps (240-250) may also be included. Figure 3 The flowchart of a pose deviation determination method provided in one embodiment of this application is shown. Figure 2 .

[0052] Step 240: Display the target page.

[0053] Optionally, the target page includes a prompt icon. Optionally, the target page includes, but is not limited to, a real-view navigation page, a navigation page, etc. The embodiments of this application do not limit the type of the target page, and the target page can be selected according to the specific application scenario.

[0054] The aforementioned augmented reality (AR) navigation page can be the navigation page of a map application, implemented using augmented reality technology. This AR navigation page includes real-time footage captured by a camera. Optionally, the camera is mounted on the target platform, such as a vehicle, ship, or aircraft. The aforementioned prompts are used to indicate navigation direction information.

[0055] Optionally, the aforementioned prompts may include, but are not limited to, directional signs, text signs, image signs, and voice signs.

[0056] Step 250: In response to the position calibration command, determine whether the target carrier is in a stationary state.

[0057] There are multiple ways to trigger the above-mentioned position calibration command, and this application embodiment does not limit this one.

[0058] In one possible implementation, the target page includes a location calibration option; in response to a selection operation for the location calibration option, such as clicking, the location calibration instruction can be triggered, and subsequent steps can be executed.

[0059] In one possible implementation, the location calibration command is triggered in response to the augmented reality navigation activation command corresponding to the aforementioned map application. Calibrating the installation deviation angle of the motion sensor during the initial stage of augmented reality navigation helps improve navigation accuracy.

[0060] In one possible implementation, the terminal can collect voice data, and if the voice data includes the target voice command, then the location calibration command is triggered.

[0061] The terminal can determine whether the target carrier is in a stationary state based on the motion data corresponding to the target carrier. This application embodiment does not limit the determination method.

[0062] In one example, such as Figure 4 As shown, it exemplifies a schematic diagram of a real-view navigation page. Figure 1 . Figure 4 The diagram shows a real-view navigation page 40 of a map navigation application in test mode, including a prompt icon 41 and a calibration option 42. The prompt icon 41 indicates the navigation direction, and the calibration option 42 triggers the aforementioned location calibration command. In response to a selection operation on the calibration option 42, such as clicking, the location calibration command is triggered, and corresponding steps are performed to calibrate the installation deviation angle of the motion sensor.

[0063] In practical applications, there are various methods for acquiring the target acceleration data corresponding to the motion sensor in real time, and this application embodiment does not limit this method. In one possible implementation, such as... Figure 3 As shown, the process of acquiring the target acceleration data corresponding to the motion sensor in real time may include the following steps (211-212).

[0064] Step 211: Acquire the raw acceleration data collected by the motion sensor within the target period in real time.

[0065] Since the target carrier is stationary, the influence of angular velocity on determining the installation deviation angle is negligible. Therefore, the installation deviation angle can be determined using only the collected acceleration data.

[0066] Optionally, the target period includes a period corresponding to a preset duration before the trigger time corresponding to the position calibration command, a period corresponding to a preset duration after the trigger time, and a period including the trigger time and having a preset duration. The target period can be flexibly adjusted according to the actual implementation method, and the embodiments of this application do not limit it in this regard.

[0067] The aforementioned raw acceleration data is real-time acceleration data, which can reflect the force information of the motion sensor during the target period, such as the magnitude of the force, the change in force, and the change in velocity.

[0068] In one possible implementation, the motion sensor's coordinate system is a three-dimensional Cartesian coordinate system constructed with a preset point within the motion sensor as the origin and three preset mutually perpendicular directions. Optionally, the sensor coordinate system includes a first coordinate axis, a second coordinate axis, and a third coordinate axis, wherein the direction corresponding to the first coordinate axis is the first direction, the direction corresponding to the second coordinate axis is the second direction, and the direction corresponding to the third coordinate axis is the third direction. The motion sensor can collect its own acceleration component data in the three directions of the sensor coordinate system.

[0069] Optionally, the aforementioned raw acceleration data includes multiple sets of acceleration data. Each set of acceleration data includes the first acceleration component data corresponding to the first direction dimension of the motion sensor in the sensor coordinate system, the second acceleration component data corresponding to the second direction dimension, and the third acceleration component data corresponding to the third direction dimension.

[0070] Optionally, the aforementioned raw acceleration data is the raw acceleration data collected by the motion sensor within the target period at a preset frequency. Optionally, the preset frequency is greater than or equal to 10 Hz, the preset duration corresponding to the target period is 2 seconds, and the aforementioned multiple sets of acceleration data include at least a preset number of sets of acceleration data, wherein the preset number is 20, to ensure the reliability and accuracy of the installation deviation angle determination.

[0071] Optionally, the motion sensor described above is a triaxial accelerometer.

[0072] Step 212: Average the raw acceleration data to obtain the target acceleration data.

[0073] There are various methods for averaging the raw acceleration data, and this application does not limit the specific methods used in the embodiments.

[0074] In one possible implementation, such as Figure 5 As shown, the implementation process of step 212 above may include the following steps (2121-2123), Figure 5 The flowchart of a pose deviation determination method provided in one embodiment of this application is shown. Figure 2 .

[0075] Step 2121: Obtain the acquisition timestamp corresponding to the raw acceleration acquisition data.

[0076] The above-mentioned acquisition timestamps are used to characterize the acquisition time corresponding to the original acceleration acquisition data.

[0077] Step 2122: Determine the weight information corresponding to the original acceleration data based on the collection timestamp.

[0078] Optionally, the aforementioned weight information includes weight values. The correspondence between weight values ​​and acquisition timestamps is obtained. Based on this correspondence and the acquisition timestamps, the weight values ​​corresponding to the raw acceleration acquisition data can be determined.

[0079] Optionally, the above weight values ​​are positively correlated with the collection timestamp; the closer the collection time is to the end of the target period, the greater the weight value corresponding to the collection time.

[0080] Based on the acquisition time corresponding to each set of acceleration data in the raw acceleration data, a weight value corresponding to its corresponding acquisition time is assigned to each set of acceleration data. Optionally, the weights corresponding to the acceleration components in different directions within each set of acceleration data can be the same, but they can also be different.

[0081] Step 2123: Based on the weight information, perform weighted averaging on the raw acceleration data to obtain the target acceleration data.

[0082] Optionally, each set of acceleration data in the original acceleration data is multiplied by its corresponding weight value to obtain the weight data corresponding to each set of acceleration data; the weight data is summed to obtain the weight data sum; and then the weight data sum is compared with the sum of the weight values ​​corresponding to each set of acceleration data to obtain the target acceleration data mentioned above.

[0083] Optionally, the above target acceleration data can be calculated using the following formula (1).

[0084]

[0085] in,,, This represents the target acceleration data, i.e., the average acceleration data, p0, p1, ..., p nThese represent the acceleration data collected in the 1st, 2nd, ..., n+1th sampling sessions, respectively, where m0, m1, ..., m n Let p0, p1, ..., p be the numbers respectively. n The corresponding weight value.

[0086] Optionally, the first acceleration component data in each set of acceleration acquisition data is multiplied by its corresponding weight value to obtain the first weight data corresponding to the first direction dimension of each set of acceleration acquisition data; the first weight data is summed to obtain the first weight data sum; and the first weight data sum is then compared with the sum of the weight values ​​corresponding to each set of acceleration acquisition data to obtain the average data of the first acceleration component.

[0087] Optionally, the second acceleration component data in each set of acceleration acquisition data is multiplied by its corresponding weight value to obtain the second weight data corresponding to the second direction dimension of each set of acceleration acquisition data; the second weight data is summed to obtain the second weight data sum; and the second weight data sum is then compared with the sum of the weight values ​​corresponding to each set of acceleration acquisition data to obtain the average data of the second acceleration component.

[0088] Optionally, the third acceleration component data in each set of acceleration data is multiplied by its corresponding weight value to obtain the third weight data corresponding to each set of acceleration data in the third dimension; the third weight data is summed to obtain the third weight data sum; and the third weight data sum is then compared with the sum of the weight values ​​corresponding to each set of acceleration data to obtain the average data of the third acceleration component.

[0089] The aforementioned target acceleration data includes the average data of the first acceleration component, the average data of the second acceleration component, and the average data of the third acceleration component. The average data of the first acceleration component is the average acceleration component data corresponding to the first direction dimension of the motion sensor in the sensor coordinate system; the average data of the second acceleration component is the average acceleration component data corresponding to the second direction dimension of the motion sensor in the sensor coordinate system; and the average data of the third acceleration component is the average acceleration component data corresponding to the third direction dimension of the motion sensor in the sensor coordinate system.

[0090] In another possible implementation, at least a preset number of sets of acceleration data are averaged to obtain target acceleration data. This includes: averaging the first acceleration component data in each set of acceleration data to obtain average data for the first acceleration component; averaging the second acceleration component data in each set of acceleration data to obtain average data for the second acceleration component; and averaging the third acceleration component data in each set of acceleration data to obtain average data for the third acceleration component.

[0091] By averaging the raw acceleration data to determine the target acceleration, the accuracy of the installation deviation angle determination can be improved. This effectively eliminates the influence of abnormal data on the final calculation result, and the averaging method maintains accuracy while reducing computational load. For example, in another implementation, the installation deviation angle can be determined for each set of acceleration data acquired within the target period. Then, the installation deviation angles corresponding to each set of acceleration data are averaged or weighted to determine the final installation deviation angle. Compared to this implementation method, the same accuracy can be guaranteed simply by averaging or weighting the acceleration data, but the computational load is greatly reduced.

[0092] Furthermore, the method described above, which determines the weight by the acquisition time and performs a weighted average of the raw acceleration acquisition data, can further improve the accuracy and real-time performance of the installation deviation angle determination. For acquisition data closer to the current time, a higher weight can be assigned, thus ensuring the accuracy and real-time performance of the installation deviation angle determination.

[0093] Step 220: Based on the target acceleration data, determine the steering information corresponding to the sensor coordinate system.

[0094] Optionally, the aforementioned sensor coordinate system is the coordinate system corresponding to the aforementioned motion sensor. Optionally, the aforementioned steering information is used to characterize the positional transformation relationship between the sensor coordinate system and the carrier coordinate system corresponding to the target carrier. Optionally, the aforementioned installation deviation angle between the aforementioned motion sensor and the target carrier is associated with the aforementioned steering information, and the aforementioned installation deviation angle includes the installation error angle between the motion sensor and the target carrier.

[0095] After obtaining the target acceleration data, the positional transformation relationship between the sensor coordinate system and the carrier coordinate system can be determined solely from this data. Because the target carrier is stationary, the carrier coordinate system and the gravity coordinate system are in the same or similar direction. The target sensor data corresponding to the motion sensor in the stationary state is positively correlated with its own gravity, and each component of the target sensor data reflects the acceleration component information of the motion sensor in the sensor coordinate system. This characterizes the component force information of the motion sensor's own gravity in each direction within the sensor coordinate system, thus determining the positional transformation relationship between the sensor coordinate system and the gravity coordinate system. Since the carrier coordinate system and the gravity coordinate system are in the same or similar direction, the positional transformation relationship between the sensor coordinate system and the carrier coordinate system can be derived, generating the aforementioned steering information. This steering information is related to the deflection angles of the sensor coordinate system and the carrier coordinate system in each direction. Therefore, in subsequent steps, this deflection angle can be determined based on the steering information. This deflection angle is the same as the installation deviation angle, thus determining the installation deviation angle of the motion sensor.

[0096] In an exemplary embodiment, such as Figure 3 As shown, the implementation process of step 220 above includes the following steps (221 to 222).

[0097] Step 221: Based on the target acceleration data, determine the steering vector corresponding to the sensor coordinate system in the target dimension.

[0098] Optionally, the target dimensions mentioned above include the first direction dimension corresponding to the first coordinate axis, the second direction dimension corresponding to the second coordinate axis, and the third direction dimension corresponding to the third coordinate axis in the sensor coordinate system.

[0099] In one possible implementation, such as Figure 5 As shown, the implementation process of step 221 above may include the following steps (2211 to 2214).

[0100] Step 2211: Normalize the target acceleration data to obtain normalized acceleration data.

[0101] Optionally, the normalized acceleration data includes first-direction acceleration data corresponding to the first direction dimension, second-direction acceleration data corresponding to the second direction dimension, and third-direction acceleration data corresponding to the third direction dimension. Optionally, the normalized acceleration data includes second-direction acceleration data corresponding to the second direction dimension, which can be used for the transformation processing in step 2213 below.

[0102] During the normalization process, the magnitude of the target acceleration data is first determined, i.e., the modulus of the target acceleration data.

[0103] In the previous steps, the average data of the first acceleration component, the average data of the second acceleration component, and the average data of the third acceleration component in the target acceleration data were obtained; based on the above average data of the first acceleration component, the average data of the second acceleration component, and the average data of the third acceleration component, the magnitude of the target acceleration data can be determined.

[0104] Optionally, the sum of squares corresponding to the average data of the first acceleration component, the average data of the second acceleration component, and the average data of the third acceleration component is determined, and the square root of the sum of squares is taken to obtain the modulus of the target acceleration data. For details, please refer to the following formula (2).

[0105]

[0106] Where ax is the average acceleration The acceleration component on the x-axis, i.e., the average data of the first acceleration component mentioned above; ay is the average acceleration. The acceleration component on the y-axis, i.e., the average data of the second acceleration component; az is the average acceleration. The acceleration components on the x-axis and the acceleration components on the z-axis, i.e., the average data of the third acceleration component mentioned above; the z-axis is the first coordinate axis mentioned above, the x-axis is the second coordinate axis mentioned above, and the y-axis is the third coordinate axis mentioned above; n is the magnitude of the target acceleration data.

[0107] Optionally, the ratio of the magnitude of the average data of the first acceleration component to the magnitude of the target acceleration data is determined to obtain the acceleration data in the first direction; the ratio of the magnitude of the average data of the second acceleration component to the magnitude of the target acceleration data is determined to obtain the acceleration data in the second direction; and the ratio of the magnitude of the average data of the third acceleration component to the magnitude of the target acceleration data is determined to obtain the acceleration data in the third direction.

[0108] The aforementioned first-direction acceleration data is normalized data corresponding to the average data of the first acceleration component, the aforementioned second-direction acceleration data is normalized data corresponding to the average data of the second acceleration component, and the aforementioned third-direction acceleration data is normalized data corresponding to the average data of the third acceleration component.

[0109] Step 2212: Based on the normalized acceleration data, determine the first steering vector corresponding to the first directional dimension.

[0110] Optionally, the first direction acceleration data, the second direction acceleration data, and the third direction acceleration data in the normalized acceleration data are arranged to generate the aforementioned first steering vector. Optionally, the aforementioned first steering vector is the first column vector corresponding to the steering matrix. The specific relationship can be found in the following formula (3).

[0111]

[0112] Where nz is the aforementioned first steering vector. The above acceleration data in the first direction, The above-mentioned acceleration data in the second direction, The above refers to the acceleration data in the first direction.

[0113] Step 2213: Based on the acceleration data in the second direction, transform the first steering vector to obtain the second steering vector corresponding to the second direction dimension.

[0114] Optionally, obtain the unit vector in the second direction (the second coordinate axis, i.e., the x-axis); multiply the acceleration data in the second direction with the first steering vector to obtain the multiplication result; perform a difference operation between the unit vector in the second direction and the multiplication result to obtain the second steering vector. Optionally, the second steering vector is the second column vector corresponding to the steering matrix. The specific relationship can be found in the following formula (4).

[0115]

[0116] Where nx is the second steering vector mentioned above, and nz is the first steering vector mentioned above. Here are the acceleration data in the second direction mentioned above, and [1 0 0] is the unit vector in the second direction mentioned above.

[0117] Step 2214: Perform a cross product on the first and second steering vectors to obtain the third steering vector corresponding to the third directional dimension.

[0118] Optionally, the third steering vector can be determined using the following formula. Optionally, the third steering vector is the third column vector corresponding to the steering matrix.

[0119] ny=|nz×nx| Formula (5)

[0120] Where ny is the third steering vector, nz is the first steering vector, and nx is the second steering vector.

[0121] Step 222: The steering vectors are fused to obtain the steering matrix.

[0122] Steering information includes the steering matrix.

[0123] Optionally, the first steering vector is transposed to obtain the first column vector corresponding to the steering matrix; the second steering vector is transposed to obtain the second column vector corresponding to the steering matrix; the third steering vector is transposed to obtain the third column vector corresponding to the steering matrix; and the steering matrix is ​​obtained based on the first, second, and third column vectors.

[0124] Alternatively, the steering matrix can be determined by the following formula (6).

[0125]

[0126] in, This represents the steering matrix described above.

[0127] Step 230: Determine the pose deviation information corresponding to the target sensor based on the steering information.

[0128] The aforementioned pose deviation information is used to characterize the installation deviation angle of the motion sensor. Optionally, the installation deviation angle includes the installation error angle of the motion sensor.

[0129] When the target carrier is stationary, the carrier coordinate system and the gravity coordinate system are oriented in the same or similar directions. The target sensor data corresponding to the motion sensor in the stationary state is positively correlated with its own gravity, and each component of the target sensor data can reflect the acceleration component information of the motion sensor in the sensor coordinate system. This can characterize the force component information of the motion sensor's own gravity in each direction in the sensor coordinate system, thereby determining the position transformation relationship between the sensor coordinate system and the gravity coordinate system. Since the carrier coordinate system and the gravity coordinate system are oriented in the same or similar directions, the position transformation relationship between the sensor coordinate system and the carrier coordinate system can be derived, generating the aforementioned steering information. The aforementioned steering information is related to the deflection angle of the sensor coordinate system and the carrier coordinate system in each direction. Therefore, in subsequent steps, the pose deviation information can be determined based on the steering information. The pose deviation information can be the angle information corresponding to the deflection angle, and since this deflection angle is the same as the installation deviation angle, the installation deviation angle of the motion sensor can be determined.

[0130] In an exemplary embodiment, such as Figure 3 As shown, the implementation process of step 230 above may include the following steps (231 to 234).

[0131] Step 231: Obtain the angle information transformation matrix.

[0132] The angle information transformation matrix includes angle parameters.

[0133] In one possible implementation, the installation deviation angle can be represented by a quaternion. Accordingly, the aforementioned angle parameter is a quaternion parameter, including a first parameter, a second parameter, a third parameter, and a fourth parameter.

[0134] Quaternions are simple hypercomplex numbers. Quaternions are all composed of real numbers plus three imaginary units i, j, and k, and each quaternion is a linear combination of 1, i, j, and k.

[0135] Optionally, the first parameter is a real parameter in the quaternion, and the second, third, and fourth parameters are the coefficient parameters corresponding to the imaginary units i, j, and k, respectively.

[0136] Optionally, the elements in the angle information transformation matrix are parameter expressions, and each parameter expression includes at least one of the first parameter, second parameter, third parameter and fourth parameter.

[0137] Step 232: Determine the correspondence between matrix elements of the angle information conversion matrix and the steering matrix.

[0138] In one possible implementation, converting the transformation matrix into an angle vector requires obtaining the transformation relationship information between the transformation matrix and the angle vector; based on the aforementioned angle information, the transformation matrix can determine the transformation relationship information.

[0139] Determining the transformation relationship requires first establishing the correspondence between the matrix elements of the angle information transformation matrix and the steering matrix. Optionally, this correspondence is a relationship where matrix elements at corresponding positions are equal. Based on this correspondence, each element in the steering matrix can be associated with a parameter expression in the angle information transformation matrix; for example, the element at the target position in the steering matrix is ​​equal to the parameter expression at the target position in the angle information transformation matrix.

[0140] Step 233: Determine the angle data corresponding to the angle parameters based on the matrix element correspondence.

[0141] Accordingly, by determining the correspondence between the matrix elements, a set of target equations can be established based on these correspondences; by solving the set of target equations, the angle data corresponding to the first, second, third, and fourth parameters can be determined.

[0142] Alternatively, the correspondence between the matrix elements can be reflected by the following formula (7).

[0143]

[0144] Wherein, q0 is the first parameter mentioned above, q1 is the second parameter mentioned above, q2 is the third parameter mentioned above, and q3 is the fourth parameter mentioned above. This is the steering matrix.

[0145] Based on the above formula (7), the first angle data corresponding to the first parameter, the second angle data corresponding to the second parameter, the third angle data corresponding to the third parameter, and the fourth angle data corresponding to the fourth parameter can be determined.

[0146] The geometric meaning of the imaginary units i, j, and k in quaternions can be understood as a kind of rotation. The i rotation represents the rotation from the positive z-axis to the positive y-axis in the plane where the z-axis and y-axis intersect. The j rotation represents the rotation from the positive x-axis to the positive z-axis in the plane where the x-axis and z-axis intersect. The k rotation represents the rotation from the positive y-axis to the positive x-axis in the plane where the y-axis and x-axis intersect. -i, -j, and -k represent the reverse rotations of i, j, and k, respectively.

[0147] Optionally, the first angle data mentioned above is real number data in quaternions; the second angle data is used to characterize the angular rotation amount corresponding to the imaginary unit i, that is, the rotation amount from the positive z-axis to the positive y-axis in the plane where the z-axis (first coordinate axis) and y-axis (third coordinate axis) intersect; the third angle data is used to characterize the angular rotation amount corresponding to the imaginary unit j, that is, the rotation amount from the positive x-axis to the positive z-axis in the plane where the x-axis (second coordinate axis) and z-axis intersect; and the fourth angle data is used to characterize the angular rotation amount corresponding to the imaginary unit k, that is, the rotation amount from the positive y-axis to the positive x-axis in the plane where the y-axis and x-axis intersect.

[0148] Step 234: Based on the angle data, determine the angle vector corresponding to the installation deviation angle.

[0149] The pose deviation information mentioned above includes the angle vector.

[0150] Accordingly, after determining the first angle data, second angle data, third angle data, and fourth angle data in the aforementioned steps, a quaternion vector, namely the aforementioned angle vector, can be generated.

[0151] Optionally, the angle vector determined based on the above formula (7) is (q0, q1, q2, q3).

[0152] The process of determining the angle vector described above is briefly explained below with reference to the diagram. Please refer to the diagram. Figure 6 , Figure 6 An exemplary flowchart illustrating the process of determining the angle vector is shown. Figure 6 In the process shown, firstly, multiple sets of data acquired by the motion sensor are weighted and averaged to obtain the average value of acceleration components in each direction; based on the above average value of acceleration components, the real-time acceleration data in the static state can be determined; then the real-time acceleration data is normalized to calculate the column vector in the steering matrix; then the steering matrix is ​​converted into a quaternion vector, and the above quaternion vector is the above angle vector.

[0153] In an exemplary embodiment, such as Figure 3 As shown, after step 230 above, step 260 may also be included.

[0154] Step 260: Based on the pose deviation information, update the display status of the prompt icon on the target page.

[0155] Since the installation deviation angle of the motion sensor is determined in real time, the corresponding calculation task can be performed based on the latest determined installation deviation angle to compensate for the deviation angle.

[0156] Optionally, based on the pose deviation information that can characterize the installation deviation angle, angle compensation information can be generated, and the display status of the prompt label on the real-view navigation page can be updated based on the angle compensation information.

[0157] Optionally, the above display status includes the display position of the prompt icon, the scaling factor, the display angle, etc.

[0158] In one example, such as Figure 7 As shown, it exemplifies a schematic diagram of a real-view navigation page. Figure 2 . Figure 7 This shows the display content of the real-view navigation page 40 after the above installation deviation angle calibration is completed, compared to... Figure 6 The display content of the real-view navigation page 40 and the display status of the indicator 41 have changed. Figure 7 The display position of the prompt icon 41 in the real-world image is more accurate, and the content in the calibration option 42 is updated to "Completed", prompting the user that the installation deviation angle calibration is complete.

[0159] In summary, the technical solution provided in this application can determine the steering information that characterizes the positional transformation relationship between the sensor coordinate system and the carrier coordinate system by acquiring the acceleration data of the motion sensor in real time when the carrier is stationary. Thus, the pose deviation information corresponding to the current installation deviation angle of the motion sensor can be determined based on the steering information, which reduces the amount of calculation required to determine the pose deviation information and improves the efficiency and accuracy of the pose deviation information determination.

[0160] In a typical application scenario of this application embodiment, such as an AR navigation scenario, this application embodiment only uses an accelerometer to quickly calibrate the angle during the installation deviation angle calibration process, which greatly reduces the use of sensors and the complexity of calculating the installation deviation angle, and improves the operating efficiency of calibrating the installation deviation angle on a vehicle terminal with poor performance.

[0161] Compared to related technical solutions that use complementary filtering or Kalman filtering to calculate vehicle angles, in scenarios where only the installation deviation angle needs to be calculated and the vehicle attitude angle does not require real-time calculation, this method of angle estimation and observation cannot quickly respond to the requirements of installation deviation angle calibration. The technical solution provided in this application can significantly reduce the computational load, quickly calibrate the installation deviation angle, reduce the system computational load of map navigation applications during the initialization process, reduce the possibility of system lag during installation deviation angle initialization, improve positioning accuracy, and reduce system performance loss.

[0162] The following are embodiments of the apparatus of this application, which can be used to execute embodiments of the method of this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the method of this application.

[0163] Please refer to Figure 8This diagram illustrates a block diagram of a pose deviation determination device according to an embodiment of this application. The device has the function of implementing the above-described pose deviation determination method; this function can be implemented in hardware or by hardware executing corresponding software. The device can be a computer device or can be installed within a computer device. The device 800 may include: an acceleration data acquisition module 810, a steering information determination module 820, and a pose deviation determination module 830.

[0164] The acceleration data acquisition module 810 is used to acquire target acceleration data corresponding to the motion sensor in real time when the target carrier is stationary. The motion sensor is installed on the vehicle-mounted equipment, and the vehicle-mounted equipment is installed on the target carrier. The target acceleration data is used to characterize the force information of the motion sensor.

[0165] The steering information determination module 820 is used to determine the steering information corresponding to the sensor coordinate system based on the target acceleration data. The sensor coordinate system is the coordinate system corresponding to the motion sensor. The steering information is used to characterize the position transformation relationship between the sensor coordinate system and the carrier coordinate system corresponding to the target carrier.

[0166] The pose deviation determination module 830 is used to determine the pose deviation information corresponding to the target sensor based on the steering information. The pose deviation information is used to characterize the installation deviation angle of the motion sensor.

[0167] In an exemplary embodiment, the steering information determination module 820 includes: a steering vector determination unit and a steering matrix determination unit.

[0168] The steering vector determination unit is used to determine the steering vector corresponding to the sensor coordinate system in the target dimension based on the target acceleration data.

[0169] A steering matrix determination unit is used to perform fusion processing on the steering vector to obtain a steering matrix, wherein the steering information includes the steering matrix.

[0170] In an exemplary embodiment, the target dimension includes a first direction dimension corresponding to a first coordinate axis, a second direction dimension corresponding to a second coordinate axis, and a third direction dimension corresponding to a third coordinate axis in the sensor coordinate system; the steering vector determination unit includes: a data normalization subunit, a first vector determination subunit, a second vector determination subunit, and a third vector determination subunit.

[0171] The data normalization subunit is used to normalize the target acceleration data to obtain normalized acceleration data, wherein the normalized acceleration data includes the second-direction acceleration data corresponding to the second-direction dimension.

[0172] The first vector determination subunit is used to determine the first steering vector corresponding to the first directional dimension based on the normalized acceleration data.

[0173] The second vector determination subunit is used to transform the first steering vector based on the second direction acceleration data to obtain the second steering vector corresponding to the second direction dimension.

[0174] The third vector determination subunit is used to perform a cross product of the first steering vector and the second steering vector to obtain the third steering vector corresponding to the third third directional dimension.

[0175] In an exemplary embodiment, the pose deviation determination module 830 includes: a transformation matrix acquisition unit, a matrix relationship determination unit, an angle data determination unit, and an angle vector determination unit.

[0176] The transformation matrix acquisition unit is used to acquire the angle information transformation matrix, which includes angle parameters.

[0177] The matrix relationship determination unit is used to determine the matrix element correspondence between the angle information conversion matrix and the steering matrix.

[0178] An angle data determination unit is used to determine the angle data corresponding to the angle parameter based on the correspondence of the matrix elements.

[0179] An angle vector determination unit is used to determine the angle vector corresponding to the installation deviation angle based on the angle data, wherein the pose deviation information includes the angle vector.

[0180] In an exemplary embodiment, the acceleration data acquisition module 810 includes: a data acquisition unit and a target acceleration determination unit.

[0181] The data acquisition unit is used to acquire the raw acceleration data collected by the motion sensor within the target period in real time.

[0182] The target acceleration determination unit is used to perform average processing on the raw acceleration data to obtain the target acceleration data.

[0183] In an exemplary embodiment, the target acceleration determination unit includes: a timestamp determination subunit, a weight determination subunit, and a target acceleration determination subunit.

[0184] The timestamp determination subunit is used to obtain the acquisition timestamp corresponding to the original acceleration acquisition data.

[0185] The weight determination subunit is used to determine the weight information corresponding to the original acceleration data based on the acquisition timestamp.

[0186] The target acceleration determination subunit is used to perform weighted averaging on the raw acceleration data based on the weight information to obtain the target acceleration data.

[0187] In an exemplary embodiment, the device 800 further includes: a page display module, a carrier status determination module, and a page update module.

[0188] A page display module is used to display a target page, which includes a prompt icon.

[0189] The carrier status determination module is used to determine whether the target carrier is in a stationary state in response to the position calibration command.

[0190] The page update module is used to update the display status of the prompt icon on the target page based on the pose deviation information.

[0191] In summary, the technical solution provided in this application can determine the steering information that characterizes the positional transformation relationship between the sensor coordinate system and the carrier coordinate system by acquiring the acceleration data of the motion sensor in real time when the carrier is stationary. Thus, the pose deviation information corresponding to the current installation deviation angle of the motion sensor can be determined based on the steering information, which reduces the amount of calculation required to determine the pose deviation information and improves the efficiency and accuracy of the pose deviation information determination.

[0192] It should be noted that the apparatus provided in the above embodiments is only illustrated by the division of the above functional modules when implementing its functions. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0193] Please refer to Figure 9 This diagram illustrates a structural block diagram of a computer device according to an embodiment of this application. The computer device may be a terminal. This computer device is used to implement the pose deviation determination method provided in the above embodiments. Specifically:

[0194] Typically, computer device 900 includes a processor 901 and a memory 902.

[0195] Processor 901 may include one or more processing cores, such as a quad-core processor, an octa-core processor, etc. Processor 901 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field Programmable Gate Array), and PLA (Programmable Logic Array). Processor 901 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, processor 901 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, processor 901 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0196] The memory 902 may include one or more computer-readable storage media, which may be non-transitory. The memory 902 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments, the non-transitory computer-readable storage media in the memory 902 is used to store at least one instruction, at least one program, code set, or instruction set, configured to be executed by one or more processors to implement the pose deviation determination method described above.

[0197] In some embodiments, the computer device 900 may optionally include a peripheral device interface 903 and at least one peripheral device. The processor 901, memory 902, and peripheral device interface 903 can be connected via a bus or signal line. Each peripheral device can be connected to the peripheral device interface 903 via a bus, signal line, or circuit board. Specifically, the peripheral device includes at least one of the following: a radio frequency circuit 904, a touch display screen 905, a camera assembly 906, an audio circuit 907, a positioning assembly 908, and a power supply 909.

[0198] Those skilled in the art will understand that Figure 9 The structure shown does not constitute a limitation on the computer device 900, and may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0199] In an exemplary embodiment, a vehicle-mounted device is also provided, wherein the vehicle-mounted device is equipped with a motion sensor, and the target carrier corresponding to the vehicle-mounted device includes a vehicle. The installation deviation angle between the motion sensor and the vehicle is determined using the aforementioned pose deviation determination method. Optionally, the motion sensor is mounted on the vehicle-mounted device, the vehicle-mounted device is mounted on the vehicle, and the vehicle is the target carrier corresponding to the motion sensor.

[0200] In an exemplary embodiment, a computer-readable storage medium is also provided, the storage medium storing at least one instruction, at least one program, code set, or instruction set, wherein the at least one instruction, the at least one program, the code set, or the instruction set, when executed by a processor, implements the above-described pose deviation determination method.

[0201] Optionally, the computer-readable storage medium may include: ROM (Read Only Memory), RAM (Random Access Memory), SSD (Solid State Drives), or optical disc, etc. The random access memory may include ReRAM (Resistance Random Access Memory) and DRAM (Dynamic Random Access Memory).

[0202] In an exemplary embodiment, a computer program product or computer program is also provided, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the aforementioned pose deviation determination method.

[0203] It should be understood that "multiple" as used herein refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. Furthermore, the step numbers described herein are merely illustrative of one possible execution order. In some other embodiments, the steps may not be executed in numerical order, such as two steps with different numbers being executed simultaneously, or two steps with different numbers being executed in the reverse order of the illustration. This application does not limit this.

[0204] In addition, in the specific embodiments of this application, data such as user information are involved. When the above embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0205] The above description is merely an exemplary embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for determining pose deviation, characterized in that, The method includes: When the target carrier is stationary, the target acceleration data corresponding to the motion sensor is acquired in real time. The motion sensor is installed on the vehicle-mounted equipment, and the vehicle-mounted equipment is installed on the target carrier. The target acceleration data is used to characterize the force information of the motion sensor. Based on the target acceleration data, the steering information corresponding to the sensor coordinate system is determined. The sensor coordinate system is the coordinate system corresponding to the motion sensor. The steering information is used to characterize the position transformation relationship between the sensor coordinate system and the carrier coordinate system corresponding to the target carrier. Based on the steering information, the pose deviation information corresponding to the motion sensor is determined, and the pose deviation information is used to characterize the installation deviation angle of the motion sensor.

2. The method according to claim 1, characterized in that, The step of determining the steering information corresponding to the sensor coordinate system based on the target acceleration data includes: Based on the target acceleration data, determine the steering vector corresponding to the sensor coordinate system in the target dimension; The steering vectors are fused to obtain a steering matrix, and the steering information includes the steering matrix.

3. The method according to claim 2, characterized in that, The target dimension includes the first direction dimension corresponding to the first coordinate axis, the second direction dimension corresponding to the second coordinate axis, and the third direction dimension corresponding to the third coordinate axis in the sensor coordinate system; Determining the steering vector of the sensor coordinate system in the target dimension based on the target acceleration data includes: The target acceleration data is normalized to obtain normalized acceleration data, which includes the second-direction acceleration data corresponding to the second-direction dimension. Based on the normalized acceleration data, determine the first steering vector corresponding to the first directional dimension; Based on the acceleration data in the second direction, the first steering vector is transformed to obtain the second steering vector corresponding to the second direction dimension. Perform a cross product on the first steering vector and the second steering vector to obtain the third steering vector corresponding to the third third-direction dimension.

4. The method according to claim 2, characterized in that, The step of determining the pose deviation information corresponding to the motion sensor based on the steering information includes: Obtain the angle information transformation matrix, which includes angle parameters; Determine the matrix element correspondence between the angle information conversion matrix and the steering matrix; Based on the correspondence of the matrix elements, determine the angle data corresponding to the angle parameter; Based on the angle data, an angle vector corresponding to the installation deviation angle is determined, and the pose deviation information includes the angle vector.

5. The method according to claim 1, characterized in that, The real-time acquisition of target acceleration data corresponding to the motion sensor includes: Real-time acquisition of raw acceleration data collected by the motion sensor within the target period; The target acceleration data is obtained by averaging the raw acceleration data.

6. The method according to claim 5, characterized in that, The step of averaging the raw acceleration data to obtain the target acceleration data includes: Obtain the acquisition timestamp corresponding to the raw acceleration acquisition data; Based on the acquisition timestamp, determine the weight information corresponding to the original acceleration acquisition data; Based on the weight information, the raw acceleration data is weighted and averaged to obtain the target acceleration data.

7. The method according to any one of claims 1 to 6, characterized in that, Before acquiring the target acceleration data corresponding to the motion sensor in real time when the target carrier is stationary, the method further includes: Display the target page, which includes a prompt icon; In response to a position calibration command, it is determined whether the target carrier is in a stationary state; After determining the pose deviation information corresponding to the motion sensor based on the steering information, the method further includes: Based on the pose deviation information, update the display status of the prompt icon on the target page.

8. A pose deviation determination device, characterized in that, The device includes: An acceleration data acquisition module is used to acquire target acceleration data corresponding to a motion sensor in real time when the target carrier is stationary. The motion sensor is installed on an in-vehicle device, and the in-vehicle device is installed on the target carrier. The target acceleration data is used to characterize the force information of the motion sensor. The steering information determination module is used to determine the steering information corresponding to the sensor coordinate system based on the target acceleration data. The sensor coordinate system is the coordinate system corresponding to the motion sensor. The steering information is used to characterize the position transformation relationship between the sensor coordinate system and the carrier coordinate system corresponding to the target carrier. The pose deviation determination module is used to determine the pose deviation information corresponding to the motion sensor based on the steering information. The pose deviation information is used to characterize the installation deviation angle of the motion sensor.

9. A computer device, characterized in that, The computer device includes a processor and a memory, the memory storing at least one instruction, at least one program, a code set, or an instruction set, the at least one instruction, the at least one program, the code set, or the instruction set being loaded and executed by the processor to implement the pose deviation determination method as described in any one of claims 1 to 7.

10. A vehicle-mounted device, characterized in that, The vehicle-mounted device is equipped with a motion sensor, and the target carrier corresponding to the vehicle-mounted device includes a vehicle. The installation deviation angle between the motion sensor and the vehicle is determined by the pose deviation determination method according to any one of claims 1 to 7.

11. A computer-readable storage medium, characterized in that, The storage medium stores at least one instruction, at least one program, code set, or instruction set, wherein the at least one instruction, the at least one program, the code set, or instruction set is loaded and executed by a processor to implement the pose deviation determination method as described in any one of claims 1 to 7.

12. A computer program product, characterized in that, The computer program product includes computer instructions stored in a computer-readable storage medium, a processor of a computer device reading the computer instructions from the computer-readable storage medium, and the processor executing the computer instructions to cause the computer device to perform the pose deviation determination method as described in any one of claims 1 to 7.

Images