Pose parameter determination method and electronic device
By acquiring attitude parameter measurements and using a deep learning model to calculate the target correction, the correction is dynamically adjusted to adapt to different scenarios. This solves the problem of low accuracy of attitude description parameters in complex scenarios, achieving more accurate attitude estimation and stronger adaptability.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- VIVO MOBILE COMM CO LTD
- Filing Date
- 2023-03-24
- Publication Date
- 2026-06-19
AI Technical Summary
In complex and ever-changing real-world application scenarios, the fixed correction values in existing technologies lack universality, resulting in low accuracy of attitude description parameters.
By acquiring the measured values of the first and second attitude parameters, a deep learning model is used to calculate the target correction amount. The correction amount is dynamically adjusted to adapt to different scenarios. The error amount and the predicted values of the second attitude parameters are combined for correction processing to obtain more accurate attitude parameters.
It improves the accuracy of correction calculation and the adaptability of fusion calculation, making attitude estimation more accurate and able to adapt to a variety of complex and ever-changing real-world application scenarios.
Smart Images
Figure CN116337073B_ABST
Abstract
Description
Technical Field
[0001] This application belongs to the field of electronic technology, specifically relating to a method for determining attitude parameters and an electronic device. Background Technology
[0002] Typically, electronic devices can estimate their attitude by fusing accelerometer and gyroscope sensors, thereby providing a data foundation for applications such as indoor navigation.
[0003] In related technologies, the correction amount can be determined manually. After determining the measurement value of the gyroscope sensor, the measurement value can be corrected by the correction amount to obtain more accurate attitude description parameters.
[0004] However, the correction amount determined by manual setting is a fixed value, which is not universally applicable in complex and ever-changing real-world application scenarios, resulting in low accuracy of the obtained attitude description parameters. Summary of the Invention
[0005] The purpose of this application is to provide a method and electronic device for determining attitude parameters, which can solve the problem that fixed correction amounts are not universal in complex and ever-changing real-world application scenarios, resulting in low accuracy of the final attitude description parameters.
[0006] In a first aspect, embodiments of this application provide a method for determining attitude parameters. The method includes: acquiring first attitude parameter measurements and second attitude parameter measurements; obtaining second attitude parameter prediction values based on the first attitude parameter measurements; correcting the first attitude parameter measurements based on a target correction amount to obtain a first attitude parameter correction value; and determining a target attitude parameter based on the first attitude parameter correction value. The target correction amount is a dynamic change amount determined based on an error and the second attitude parameter prediction value, where the error is determined based on the second attitude parameter measurements and the second attitude parameter prediction value.
[0007] Secondly, embodiments of this application provide an attitude parameter determination device, comprising: an acquisition module and a processing module; the acquisition module is configured to acquire a first attitude parameter measurement value and a second attitude parameter measurement value; the processing module is configured to obtain a second attitude parameter prediction value based on the first attitude parameter measurement value; perform correction processing on the first attitude parameter measurement value based on a target correction amount to obtain a first attitude parameter correction value; and determine a target attitude parameter based on the first attitude parameter correction value; wherein the target correction amount is a dynamic change amount determined based on an error amount and the second attitude parameter prediction value, and the error amount is determined based on the second attitude parameter measurement value and the second attitude parameter prediction value.
[0008] Thirdly, embodiments of this application provide an electronic device including a processor and a memory, the memory storing programs or instructions executable on the processor, the programs or instructions, when executed by the processor, implementing the steps of the method described in the first aspect.
[0009] Fourthly, embodiments of this application provide a readable storage medium on which a program or instructions are stored, which, when executed by a processor, implement the steps of the method described in the first aspect.
[0010] Fifthly, embodiments of this application provide a chip, the chip including a processor and a communication interface, the communication interface being coupled to the processor, the processor being used to run programs or instructions to implement the method as described in the first aspect.
[0011] In a sixth aspect, embodiments of this application provide a computer program product stored in a storage medium, which is executed by at least one processor to implement the method described in the first aspect.
[0012] In this embodiment, a first attitude parameter measurement value and a second attitude parameter measurement value can be obtained; a second attitude parameter prediction value can be obtained based on the first attitude parameter measurement value; the first attitude parameter measurement value is corrected based on a target correction amount to obtain a first attitude parameter correction value; a target attitude parameter is determined based on the first attitude parameter correction value; wherein, the target correction amount is a dynamic change amount determined based on the error amount and the second attitude parameter prediction value, and the error amount is determined based on the second attitude parameter measurement value and the second attitude parameter prediction value. Through this scheme, since the target correction amount is a dynamic change amount obtained based on the error amount and the second attitude parameter prediction value, not only is the calculation accuracy of the correction amount improved, enabling the entire fusion framework to estimate the attitude more accurately, but the adaptability of the fusion calculation is also improved, allowing it to adapt to various complex and changing practical application scenarios. Attached Figure Description
[0013] Figure 1 This is a flowchart illustrating the attitude parameter determination method provided in the embodiments of this application;
[0014] Figure 2 This is a schematic diagram of the attitude parameter fusion framework of the attitude parameter determination method provided in the embodiments of this application;
[0015] Figure 3 This is a schematic diagram of the structure of the deep learning model provided in the embodiments of this application;
[0016] Figure 4 This is a schematic diagram of the attitude parameter determination device provided in the embodiments of this application;
[0017] Figure 5 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application;
[0018] Figure 6 This is a hardware schematic diagram of the electronic device provided in the embodiments of this application. Detailed Implementation
[0019] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.
[0020] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.
[0021] The attitude parameter determination method provided in this application will be described in detail below with reference to the accompanying drawings, through specific embodiments and application scenarios.
[0022] The attitude parameter determination method provided in this application embodiment can be executed by an electronic device or a functional module or entity in an electronic device that can implement the attitude parameter determination method. The electronic devices mentioned in this application embodiment include, but are not limited to, mobile phones, tablets, computers, cameras, wearable devices, etc. The attitude parameter determination method provided in this application embodiment is described below using an electronic device as the execution subject.
[0023] like Figure 1 As shown in the figure, this application provides a method for determining attitude parameters, which may include steps 101-104:
[0024] Step 101: Obtain the measured values of the first attitude parameter and the second attitude parameter.
[0025] Optionally, the first attitude parameter measurement value is detected by an angular velocity sensor, and the second attitude parameter measurement value is detected by an accelerometer.
[0026] It should be noted that the aforementioned angular velocity sensor can also be called a gyroscope. The measured value of the first attitude parameter can be the angular velocity, and the measured value of the second attitude parameter can be the gravitational acceleration.
[0027] Specifically, such as Figure 2 As shown, electronic devices may include gyroscopes and accelerometers. An electronic device can detect its angular velocity using its built-in gyroscope and its gravitational acceleration using its built-in accelerometer, obtaining a gravitational acceleration measurement. Because accelerometers have high-frequency noise, their accuracy is limited when measuring high-speed motion. Gyroscopes can accurately measure instantaneous motion, but the measurements drift over time. Therefore, measurements from accelerometers and gyroscopes are often fused to correct and compensate for the shortcomings of individual sensor measurements.
[0028] Based on the above scheme, since the electronic device can detect the first attitude parameter measurement value through the angular velocity sensor and the second attitude parameter measurement value through the accelerometer, the two attitude parameters of the electronic device can be determined. This can provide a basis for data fusion, thereby correcting and compensating for the measurement defects of a single sensor.
[0029] Step 102: Obtain the predicted values of the second attitude parameters based on the measured values of the first attitude parameters.
[0030] Optionally, the electronic device may correct the measured value of the first attitude parameter based on the historical correction amount to obtain the corrected value of the second attitude parameter; update the second attitude parameter in the attitude description parameter to the corrected value of the second attitude parameter; and determine the predicted value of the second attitude parameter based on the updated attitude description parameter; wherein the attitude description parameter is described by any one of rotation matrix, Euler angles, and quaternion.
[0031] It should be noted that the above-mentioned historical corrections refer to the corrections obtained in the most recent historical measurement.
[0032] Specifically, please refer to Figure 2 The electronic device can first correct the angular velocity (i.e., the measured value of the first attitude parameter) obtained at time t based on the historical correction amount to obtain the corrected value of the second attitude parameter. Then, the second attitude parameter in the attitude description parameters at time (t-1) is updated with the corrected value of the second attitude parameter, thereby determining the attitude description parameter at time t. The attitude description parameter at time t can be used to describe the new attitude of the electronic device. After that, the electronic device can perform parameter decomposition in different directions based on the attitude description parameter at time t to obtain the gravitational acceleration of the electronic device (i.e., the predicted value of the second attitude parameter).
[0033] Based on the above scheme, since the predicted values of the second attitude parameters can be obtained from the measured values of the first attitude parameters, a parameter basis can be provided for the update of the correction amount.
[0034] Step 103: Correct the measured value of the first attitude parameter based on the target correction amount to obtain the corrected value of the first attitude parameter.
[0035] The target correction amount is a dynamic change amount obtained based on the error amount and the predicted value of the second attitude parameter, wherein the error amount is determined based on the measured value of the second attitude parameter and the predicted value of the second attitude parameter.
[0036] Specifically, please refer to Figure 2 After determining the predicted and measured values of gravitational acceleration, the electronic device can perform a vector cross product on the predicted and measured values to obtain the error. Then, based on a deep learning model, the electronic device can obtain a target correction value according to the error and the predicted value of gravitational acceleration. This target correction value is a dynamic variable, meaning that it can change with the difference between the measured values of the first and second attitude parameters.
[0037] Optionally, the electronic device can first input the error and the predicted values of the second attitude parameters into the deep learning model to obtain fusion parameters, which include a scaling factor k. p and integral coefficient k i Based on the formula δ=k p *Error Acc+k i ∫Error Acc determines the target correction amount.
[0038] Optionally, the deep learning model described above may include at least two GRU networks and at least two fully connected networks; wherein the activation functions of the reset gate and update gate of the at least two GRU networks are sigmoid activation functions, the activation function of the candidate hidden state is a tanh activation function, and the activation function of the at least two fully connected networks is a ReLU function.
[0039] Optionally, the above-mentioned at least two GRU networks may include a first GRU neural network and a second GRU neural network, and the at least two fully connected networks may include a first fully connected neural network and a second fully connected neural network.
[0040] For example, such as Figure 3As shown, the input vector of the deep learning model includes three components of the predicted gravitational acceleration and three components of the error. The three components of the predicted gravitational acceleration are PredAcx, PredAcy, and PredAcz, and the three components of the error are ErrorAcx, ErrorAcy, and ErrorAcz. The input vector is first fed into a first GRU neural network, which has 64 hidden neurons in its hidden layer and one recurrent layer. The output of the first GRU neural network is then fed into a second GRU neural network, which has the same parameters as the first GRU neural network, 64 hidden neurons in its hidden layer, and one recurrent layer. The output of the second GRU neural network is then fed into a first fully connected layer, which contains 32 neurons. The output of the first fully connected layer is then fed into a second fully connected layer, which contains 2 neurons. Finally, the output vector of the second fully connected layer is the scale factor k to be predicted. p and integral coefficient k i Afterwards, electronic devices can be based on the formula δ = k p *Error Acc+k i ∫Error Acc calculates the target correction amount δ, where Error Acc is the error amount.
[0041] Based on the above scheme, since the fusion parameters can be obtained through deep learning models, dynamic adaptive calculation of the target correction amount can be achieved, so that the target pose parameters obtained according to the fusion framework can adapt to a variety of complex and ever-changing practical application scenarios.
[0042] Optionally, after determining the target correction amount, the electronic device can determine the first attitude parameter correction value as the sum of the first attitude parameter measurement value and the target correction amount.
[0043] Based on the above scheme, since the sum of the first attitude parameter measurement value and the target correction value can be determined as the first attitude parameter correction value, the first attitude parameter measurement value can be corrected, thereby making the attitude description more accurate.
[0044] Optionally, after determining the target correction value, the electronic device can update the historical correction values to the target correction value. That is, the correction value is updated every time the angular velocity sensor and accelerometer take a measurement.
[0045] Based on the above scheme, since the historical correction amount can be updated to the target correction amount, the correction amount can be updated adaptively, thus adapting to a variety of complex and ever-changing practical application scenarios.
[0046] Step 104: Determine the target attitude parameters based on the first attitude parameter correction value.
[0047] After determining the first attitude parameter correction value, the electronic device can substitute the first attitude parameter correction value into the attitude description parameter to determine the target attitude parameter, which is used to describe the current attitude of the electronic device.
[0048] In this embodiment, since the target correction amount is a dynamic change obtained based on the error amount and the predicted value of the second attitude parameter, it not only improves the calculation accuracy of the correction amount, enabling the entire fusion framework to estimate the attitude more accurately, but also improves the adaptability of the fusion calculation, making it adaptable to a variety of complex and ever-changing practical application scenarios.
[0049] The attitude parameter determination method provided in this application can be executed by an attitude parameter determination device. This application uses an attitude parameter determination device executing the attitude parameter determination method as an example to illustrate the attitude parameter determination device provided in this application.
[0050] like Figure 4 As shown in the illustration, this application embodiment also provides an attitude parameter determination device 400, including: an acquisition module 401 and a processing module 402; the acquisition module 401 is used to acquire a first attitude parameter measurement value and a second attitude parameter measurement value; the processing module 402 is used to obtain a second attitude parameter prediction value based on the first attitude parameter measurement value; perform correction processing on the first attitude parameter measurement value based on a target correction amount to obtain a first attitude parameter correction value; and determine a target attitude parameter based on the first attitude parameter correction value; wherein, the target correction amount is a dynamic change amount obtained based on an error amount and the second attitude parameter prediction value, and the error amount is determined based on the second attitude parameter measurement value and the second attitude parameter prediction value.
[0051] Optionally, the processing module 402 is further configured to input the measured values of the first attitude parameters, the error, and the predicted values of the second attitude parameters into a deep learning model to obtain fusion parameters, wherein the fusion parameters include a scaling factor and an integral factor; based on the formula δ = k p *Error Acc+k i ∫Error Acc determines the target correction amount; where δ is the target correction amount, k p Let k be the proportionality coefficient. i Let be the integral coefficient, and Error Acc be the error amount.
[0052] Optionally, the processing module 402 is specifically used to determine the sum of the first attitude parameter measurement value and the target correction amount as the first attitude parameter correction value.
[0053] Optionally, the processing module 402 is specifically used to correct the measured value of the first attitude parameter based on the historical correction amount to obtain the corrected value of the second attitude parameter; update the second attitude parameter in the attitude description parameter to the corrected value of the second attitude parameter; and determine the predicted value of the second attitude parameter according to the updated attitude description parameter; wherein the attitude description parameter is described by any one of rotation matrix, Euler angle and quaternion.
[0054] Optionally, the processing module 402 is further configured to update the historical correction amount to the target correction amount.
[0055] Optionally, the acquisition module 401 is specifically used to: detect the first attitude parameter measurement value through an angular velocity sensor and detect the second attitude parameter measurement value through an accelerometer.
[0056] In this embodiment, since the target correction amount is a dynamic change obtained based on the error amount and the predicted value of the second attitude parameter, it not only improves the calculation accuracy of the correction amount, enabling the entire fusion framework to estimate the attitude more accurately, but also improves the adaptability of the fusion calculation, making it adaptable to a variety of complex and ever-changing practical application scenarios.
[0057] The attitude parameter determination device in this application embodiment can be an electronic device or a component within an electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal or other devices besides a terminal. For example, the electronic device can be a mobile phone, tablet computer, laptop computer, PDA, in-vehicle electronic device, mobile internet device (MID), augmented reality (AR) / virtual reality (VR) device, robot, wearable device, ultra-mobile personal computer (UMPC), netbook, or personal digital assistant (PDA), etc. It can also be a server, network attached storage (NAS), personal computer (PC), television (TV), ATM, or self-service machine, etc. This application embodiment does not specifically limit the device.
[0058] The attitude parameter determination device in this application embodiment can be a device with an operating system. This operating system can be Android, iOS, or other possible operating systems; this application embodiment does not specifically limit it.
[0059] The attitude parameter determination device provided in this application embodiment can achieve... Figures 1 to 3 The various processes implemented in the method implementation examples will not be described again here to avoid repetition.
[0060] Optionally, such as Figure 5 As shown, this application embodiment also provides an electronic device 500, including a processor 501 and a memory 502. The memory 502 stores a program or instructions that can run on the processor 501. When the program or instructions are executed by the processor 501, they implement the various steps of the above-described attitude parameter determination method embodiment and can achieve the same technical effect. To avoid repetition, they will not be described again here.
[0061] It should be noted that the electronic devices in the embodiments of this application include the mobile electronic devices and non-mobile electronic devices described above.
[0062] Figure 6 A schematic diagram of the hardware structure of an electronic device to implement an embodiment of this application.
[0063] The electronic device 1000 includes, but is not limited to, components such as: radio frequency unit 1001, network module 1002, audio output unit 1003, input unit 1004, sensor 1005, display unit 1006, user input unit 1007, interface unit 1008, memory 1009, and processor 1010.
[0064] Those skilled in the art will understand that the electronic device 1000 may also include a power supply (such as a battery) for supplying power to various components. The power supply may be logically connected to the processor 1010 through a power management system, thereby enabling functions such as managing charging, discharging, and power consumption through the power management system. Figure 6 The electronic device structure shown does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown, or combine certain components, or have different component arrangements, which will not be elaborated here.
[0065] The sensor 1005 is used to acquire a first attitude parameter measurement value and a second attitude parameter measurement value; the processor 1010 is used to obtain a second attitude parameter prediction value based on the first attitude parameter measurement value; to correct the first attitude parameter measurement value based on a target correction amount to obtain a first attitude parameter correction value; and to determine a target attitude parameter based on the first attitude parameter correction value; wherein the target correction amount is a dynamic change amount obtained based on the error amount and the second attitude parameter prediction value, and the error amount is determined based on the second attitude parameter measurement value and the second attitude parameter prediction value.
[0066] In this embodiment, since the target correction amount is a dynamic change obtained based on the error amount and the predicted value of the second attitude parameter, it not only improves the calculation accuracy of the correction amount, enabling the entire fusion framework to estimate the attitude more accurately, but also improves the adaptability of the fusion calculation, making it adaptable to a variety of complex and ever-changing practical application scenarios.
[0067] Optionally, the processor 1010 is further configured to input the measured values of the first attitude parameters, the error amount, and the predicted values of the second attitude parameters into a deep learning model to obtain fusion parameters, the fusion parameters including a scaling factor and an integral factor; based on the formula δ = k p *Error Acc+k i ∫Error Acc determines the target correction amount; where δ is the target correction amount, k p Let k be the proportionality coefficient. i Let be the integral coefficient, and Error Acc be the error amount.
[0068] In the embodiments of this application, since the fusion parameters can be obtained through a deep learning model, the dynamic adaptive calculation of the target correction amount can be realized, so that the target pose parameters obtained according to the fusion framework can adapt to a variety of complex and ever-changing actual use scenarios.
[0069] Optionally, the processor 1010 is specifically configured to determine the sum of the first attitude parameter measurement value and the target correction amount as the first attitude parameter correction value.
[0070] In this embodiment, since the sum of the first attitude parameter measurement value and the target correction amount can be determined as the first attitude parameter correction value, the first attitude parameter measurement value can be corrected, thereby making the attitude description more accurate.
[0071] Optionally, the processor 1010 is specifically configured to correct the measured value of the first attitude parameter based on the historical correction amount to obtain the corrected value of the second attitude parameter; update the second attitude parameter in the attitude description parameter to the corrected value of the second attitude parameter; and determine the predicted value of the second attitude parameter according to the updated attitude description parameter; wherein the attitude description parameter is described by any one of rotation matrix, Euler angle and quaternion.
[0072] In the embodiments of this application, since the predicted value of the second attitude parameter can be obtained from the measured value of the first attitude parameter, a parameter basis can be provided for the update of the correction amount.
[0073] Optionally, the processor 1010 is further configured to update the historical correction amount to the target correction amount.
[0074] In this embodiment, since the historical correction amount can be updated to the target correction amount, the correction amount can be adaptively updated, thereby adapting to a variety of complex and ever-changing practical application scenarios.
[0075] Optionally, sensor 1005 is specifically used to: detect the measured value of the first attitude parameter by means of an angular velocity sensor, and detect the measured value of the second attitude parameter by means of an accelerometer.
[0076] In this embodiment, since the electronic device can detect the first attitude parameter measurement value through the angular velocity sensor and the second attitude parameter measurement value through the accelerometer, the two attitude parameters of the electronic device can be determined. This provides a basis for data fusion, thereby correcting and compensating for the measurement defects of a single sensor.
[0077] It should be understood that, in this embodiment, the input unit 1004 may include a graphics processing unit (GPU) 10041 and a microphone 10042. The GPU 10041 processes image data of still images or videos obtained by an image capture device (such as a camera) in video capture mode or image capture mode. The display unit 1006 may include a display panel 10061, which may be configured in the form of a liquid crystal display, an organic light-emitting diode, or the like. The user input unit 1007 includes a touch panel 10071 and at least one of other input devices 10072. The touch panel 10071 is also called a touch screen. The touch panel 10071 may include a touch detection device and a touch controller. Other input devices 10072 may include, but are not limited to, physical keyboards, function keys (such as volume control buttons, power buttons, etc.), trackballs, mice, and joysticks, which will not be described in detail here.
[0078] The memory 1009 can be used to store software programs and various data. The memory 1009 may primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area may store the operating system, application programs or instructions required for at least one function (such as sound playback, image playback, etc.). Furthermore, the memory 1009 may include volatile memory or non-volatile memory, or both. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus RAM (DRRAM). The memory 1009 in this embodiment includes, but is not limited to, these and any other suitable types of memory.
[0079] The processor 1010 may include one or more processing units; optionally, the processor 1010 integrates an application processor and a modem processor, wherein the application processor mainly handles operations involving the operating system, user interface, and applications, and the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into the processor 1010.
[0080] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described attitude parameter determination method embodiments and achieve the same technical effect. To avoid repetition, they will not be described again here.
[0081] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.
[0082] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the above-described attitude parameter determination method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be described again here.
[0083] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.
[0084] This application provides a computer program product, which is stored in a storage medium and executed by at least one processor to implement the various processes of the attitude parameter determination method embodiment described above, and can achieve the same technical effect. To avoid repetition, it will not be described again here.
[0085] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.
[0086] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of 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 this application, in essence, or the part that contributes to the related technology, can be embodied in the form of a computer 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 (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.
[0087] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.
Claims
1. A method of attitude parameter determination, characterized in that include: Obtain the measured values of the first attitude parameter and the second attitude parameter; The predicted values of the second attitude parameters are determined based on the measured values of the first attitude parameters. The first attitude parameter measurement value is corrected based on the target correction amount to obtain the first attitude parameter correction value; The target attitude parameters are determined based on the first attitude parameter correction value; The target correction amount is a dynamic change amount determined based on the error amount and the predicted value of the second attitude parameter, wherein the error amount is determined based on the measured value of the second attitude parameter and the predicted value of the second attitude parameter.
2. The attitude parameter determination method according to claim 1, characterized by, Before correcting the measured value of the first attitude parameter based on the target correction amount to obtain the corrected value of the first attitude parameter, the method further includes: The error and the predicted value of the second attitude parameter are input into the deep learning model to obtain the fusion parameter, which includes a proportional coefficient and an integral coefficient. Based on the formula determining the target correction amount; wherein, is the target correction amount, is the proportional coefficient, is the integral coefficient, is the error amount.
3. The method of determining a pose parameter according to claim 1 or 2, characterized in that The step of correcting the measured value of the first attitude parameter based on the target correction amount to obtain the corrected value of the first attitude parameter includes: The sum of the first attitude parameter measurement value and the target correction value is determined as the first attitude parameter correction value.
4. The attitude parameter determination method according to claim 1, characterized by, Determining the predicted value of the second attitude parameter based on the measured value of the first attitude parameter includes: The first attitude parameter measurement value is corrected based on the historical correction value to obtain the second attitude parameter correction value. Update the second attitude parameter in the attitude description parameters to the corrected value of the second attitude parameter; The predicted value of the second attitude parameter is determined based on the updated attitude description parameters; The attitude description parameters are described by any one of rotation matrix, Euler angles, and quaternions.
5. The method of pose parameter determination according to claim 4, characterized in that, After determining the target correction amount, the method further includes: Update the historical correction amount to the target correction amount.
6. The attitude parameter determination method according to claim 1, characterized by, The acquisition of the first attitude parameter measurement value and the second attitude parameter measurement value includes: The first attitude parameter measurement value is detected by an angular velocity sensor, and the second attitude parameter measurement value is detected by an accelerometer.
7. An attitude parameter determination apparatus characterized by comprising: include: Acquisition module and processing module; The acquisition module is used to acquire the measured values of the first attitude parameter and the second attitude parameter; The processing module is used to obtain the predicted value of the second attitude parameter based on the measured value of the first attitude parameter. The measured values of the first attitude parameters are corrected based on the target correction amount to obtain the corrected values of the first attitude parameters; the target attitude parameters are then determined based on the corrected values of the first attitude parameters. The target correction amount is a dynamic change amount obtained based on the error amount and the predicted value of the second attitude parameter, wherein the error amount is determined based on the measured value of the second attitude parameter and the predicted value of the second attitude parameter.
8. The attitude parameter determination apparatus according to claim 7, characterized by The processing module is further configured to input the error amount and the predicted value of the second attitude parameter into the deep learning model to obtain the fusion parameters, the fusion parameters including the proportional coefficient and the integral coefficient; Based on the formula determining the target correction amount; wherein, is the target correction amount, is the proportional coefficient, is the integral coefficient, is the error amount.
9. The attitude parameter determination apparatus according to claim 7 or 8, characterized by The processing module is specifically used to determine the first attitude parameter correction value by summing the first attitude parameter measurement value and the target correction amount.
10. The attitude parameter determination apparatus according to claim 7, characterized by The processing module is specifically used to correct the measured value of the first attitude parameter based on the historical correction amount to obtain the corrected value of the second attitude parameter; update the second attitude parameter in the attitude description parameter to the corrected value of the second attitude parameter; and determine the predicted value of the second attitude parameter according to the updated attitude description parameter; wherein the attitude description parameter is described by any one of rotation matrix, Euler angle and quaternion.
11. The attitude parameter determination apparatus according to claim 10, characterized by The processing module is further configured to update the historical correction amount to the target correction amount.
12. The attitude parameter determination apparatus according to claim 7, characterized by The acquisition module is specifically used to: detect the measured value of the first attitude parameter through an angular velocity sensor, and detect the measured value of the second attitude parameter through an accelerometer.
13. An electronic device, comprising: It includes a processor and a memory, the memory storing a program or instructions that can run on the processor, the program or instructions being executed by the processor to implement the attitude parameter determination method as described in any one of claims 1-6.