Error compensation method and device of navigation system and readable storage medium

Abstract

The invention discloses an error compensation method and device of a navigation system and a readable storage medium. The method comprises the following steps: acquiring basic data of the navigation system, the basic data at least comprising positioning data and / or motion state data of a mobile device in the navigation system, the positioning data being used for indicating the position of the mobile device, and the motion state data being used for indicating the speed and / or direction of the mobile device; based on the basic data, an error compensation strategy of the navigation system is determined, and the error compensation strategy is used for indicating a rule for compensating the navigation system; determining error compensation parameters of the navigation system based on the basic data and the error compensation strategy; according to the error compensation parameter, the navigation system is compensated, and the error of the compensated navigation system relative to the navigation system before compensation is smaller than a target threshold value. The technical problem that the navigation system cannot operate stably is solved.

Description

Technical Field

[0001] The present invention relates to the field of navigation calibration technology, and in particular to an error compensation method, device and readable storage medium of a navigation system. Background Art

[0002] At present, in the traditional integrated navigation system, the combination of the Global Navigation Satellite System (GNSS) and the Inertial Navigation System (INS) provides high-precision position and attitude estimation for various navigation scenarios. However, GNSS signals are easily interfered by factors such as occlusion and reflection in complex environments, such as urban canyons, densely forested areas, or underground spaces, and even completely interrupted. This signal instability makes it impossible for the system to continuously provide reliable high-precision positioning information.

[0003] In the related technology, although INS can maintain the positioning function for a short period of time by relying on inertial sensors, the inherent drift, noise and cumulative error problems of the sensors cause the navigation accuracy to drop rapidly, making it difficult to meet the actual needs by using INS independently for a long time. Therefore, there is a technical problem that the navigation system cannot operate stably.

[0004] With respect to the above-mentioned technical problem that the navigation system cannot operate stably, no effective solution has been proposed so far. Summary of the invention

[0005] The embodiments of the present invention provide a navigation system error compensation method, device and readable storage medium to at least solve the technical problem that the navigation system cannot operate stably.

[0006] According to one aspect of an embodiment of the present invention, a method for error compensation of a navigation system is provided. The method may include: acquiring basic data of the navigation system, wherein the basic data at least includes positioning data and / or motion state data of a mobile device in the navigation system, the positioning data is used to indicate the position of the mobile device, and the motion state data is used to indicate the speed and / or direction of the mobile device; based on the basic data, determining an error compensation strategy of the navigation system, wherein the error compensation strategy is used to indicate a rule for compensating the navigation system; based on the basic data and the error compensation strategy, determining an error compensation parameter of the navigation system; according to the error compensation parameter, compensating the navigation system, wherein the error of the compensated navigation system relative to the navigation system before compensation is less than a target threshold.

[0007] Optionally, based on the basic data, the error compensation strategy of the navigation system is determined, including: in response to the positioning data being valid, determining the error compensation strategy of the navigation system to be a first compensation strategy; in response to the positioning data being invalid, determining the error compensation strategy of the navigation system to be a second compensation strategy; wherein the first compensation strategy and the second compensation strategy determine error compensation parameters in different ways.

[0008] Optionally, based on basic data and the error compensation strategy, error compensation parameters of the navigation system are determined, including: in response to the error compensation strategy being a first compensation strategy, inputting the motion state data into a first compensation model to obtain position increment data, wherein the first compensation model is trained using historical motion state data; and fusing the position increment data with the positioning data to obtain error compensation parameters.

[0009] Optionally, based on basic data and the error compensation strategy, error compensation parameters of the navigation system are determined, including: in response to the error compensation strategy being the second compensation strategy, inputting the positioning data into a second compensation model to obtain pseudo-position data, wherein the second compensation model is trained using historical positioning data; and fusing the pseudo-position data with the motion state data to obtain error compensation parameters.

[0010] Optionally, compensating the navigation system according to the error compensation parameter includes: inputting the error compensation parameter into the navigation system for compensation.

[0011] Optionally, before acquiring basic data of the navigation system, the error compensation method of the navigation system further includes: calibrating an inertial sensor in the navigation system.

[0012] According to another aspect of an embodiment of the present invention, an error compensation device for a navigation system is also provided. The device may include: an acquisition unit, used to acquire basic data of the navigation system, wherein the basic data at least includes positioning data and / or motion state data, the positioning data is used to indicate the position of a mobile device in the navigation system, and the motion state data is used to indicate the speed and / or direction of the mobile device in the navigation system; a first determination unit, used to determine an error compensation strategy for the navigation system based on the basic data, wherein the error compensation strategy is used to indicate a rule for compensating the navigation system; a second determination unit, used to determine an error compensation parameter for the navigation system based on the basic data and the error compensation strategy; a compensation unit, used to compensate for the error of the navigation system according to the error compensation parameter, wherein the error of the compensated navigation system relative to the error of the navigation system before compensation is less than a target threshold.

[0013] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is also provided, which includes a stored program, wherein when the program is executed by a processor, the device where the storage medium is located is controlled to execute the error compensation method of the navigation system in the embodiment of the present invention.

[0014] According to another aspect of an embodiment of the present invention, a processor is further provided. The processor is used to run a program, wherein the error compensation method of the navigation system in the embodiment of the present invention is executed when the program is run.

[0015] According to another aspect of the embodiment of the present invention, a computer program product is further provided, wherein the program product comprises computer instructions, and when the computer instructions are executed by a processor, the error compensation method of the navigation system in the embodiment of the present invention is implemented.

[0016] In an embodiment of the present invention, basic data of a navigation system is obtained, wherein the basic data at least includes positioning data and / or motion state data of a mobile device in the navigation system, the positioning data is used to indicate the position of the mobile device, and the motion state data is used to indicate the speed and / or direction of the mobile device; based on the basic data, an error compensation strategy of the navigation system is determined, wherein the error compensation strategy is used to indicate a rule for compensating the navigation system; based on the basic data and the error compensation strategy, error compensation parameters of the navigation system are determined; according to the error compensation parameters, the navigation system is compensated, wherein the error of the compensated navigation system relative to the error of the navigation system before compensation is less than a target threshold. That is to say, the present invention determines the error compensation strategy and error compensation parameters based on the basic data of the navigation system, thereby performing error compensation on the navigation system, thereby solving the technical problem that the navigation system cannot operate stably, and achieving the technical effect of improving the stability of the navigation system. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0018] Figure 1 is a flow chart of an error compensation method for a navigation system according to an embodiment of the present invention;

[0019] Figure 2 is a schematic diagram of a GNSS / INS integrated navigation error compensation method according to an embodiment of the present invention;

[0020] Figure 3 is a schematic diagram of a GNSS / INS loosely coupled structure and a Kalman filtering process according to an embodiment of the present invention;

[0021] Figure 4is a schematic diagram of a GNSS / INS integrated navigation system model training phase according to an embodiment of the present invention;

[0022] Figure 5 is a schematic diagram of a GNSS / INS integrated navigation system model prediction stage according to an embodiment of the present invention;

[0023] Figure 6 is a schematic diagram of an error compensation device for a navigation system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0024] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0025] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, functional component or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, functional components or devices.

[0026] According to an embodiment of the present invention, an embodiment of an error compensation method for a navigation system is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0027] Figure 1 is a flow chart of an error compensation method for a navigation system according to an embodiment of the present invention. Figure 1 As shown, the method may include the following steps:

[0028] Step S101, obtaining basic data of the navigation system.

[0029] In the technical solution provided in the above step S101 of the present invention, the basic data at least includes the positioning data and / or motion state data of the mobile device in the navigation system, the positioning data is used to indicate the position of the mobile device, and the motion state data is used to indicate the speed and / or direction of the mobile device. The positioning data of the mobile device may be GNSS data, and the motion state data may be INS data.

[0030] In this embodiment, basic data of the navigation system is obtained, for example, using a GNSS receiver and an INS sensor to obtain the basic data of the navigation system. This is only an illustrative example and does not limit the specific method of obtaining the basic data of the navigation system.

[0031] Optionally, by acquiring the positioning data and motion status data of the mobile device in the navigation system, the accuracy and reliability of positioning and navigation can be improved.

[0032] Step S102: determining an error compensation strategy of the navigation system based on basic data.

[0033] In the technical solution provided in the above step S102 of the present invention, the error compensation strategy is used to indicate the rules for compensating the navigation system.

[0034] In this embodiment, after the basic data of the navigation system is acquired in step S101, an error compensation strategy of the navigation system is determined according to the basic data.

[0035] Optionally, when the positioning data is valid, it means that the received satellite signal is strong and stable enough to provide accurate location information. Based on this, the error compensation strategy of the navigation system can be determined to be the first compensation strategy; when the positioning data is invalid, it means that the received satellite signal is unstable. Based on this, the error compensation strategy of the navigation system can be determined to be the second compensation strategy; wherein the first compensation strategy and the second compensation strategy determine the error compensation parameters in different ways.

[0036] Step S103: determining error compensation parameters of the navigation system based on the basic data and the error compensation strategy.

[0037] In the technical solution provided in the above step S103 of the present invention, after the error compensation strategy of the navigation system is determined in step S102, the error compensation parameters of the navigation system are determined according to the basic data and the error compensation strategy.

[0038] In this embodiment, when the error compensation strategy is the first compensation strategy, the motion state data is input into the first compensation model to obtain position increment data, wherein the first compensation model is trained using historical motion state data, thereby fusing the position increment data with the positioning data to obtain error compensation parameters.

[0039] For example, when GNSS data is available, the first compensation model is trained using historical INS data, where the input and output of the first compensation model can be expressed as the following formula (1):

[0040] Input:[θγψf X f Y f Z ω X ω Y ω Z ]

[0041]

[0042] According to the first compensation model, the position increment of GNSS is output, and then combined with the original data of GNSS for filtering and fusion to obtain the error compensation parameter. Among them, the position increment can be expressed in the quadratic integral form of the specific force equation, as shown in the following formula (2):

[0043]

[0044] Optionally, in response to the error compensation strategy being the second compensation strategy, the positioning data is input into a second compensation model to obtain pseudo-position data, wherein the second compensation model is trained using historical positioning data, thereby fusing the pseudo-position data with the motion state data to obtain error compensation parameters.

[0045] For example, when the GNSS signal is unavailable, the second compensation model is trained using historical positioning data, and pseudo GNSS data is output according to the second compensation model, wherein the pseudo GNSS data is calculated as shown in the following formula (3):

[0046]

[0047] in, is the pseudo GNSS data at time k, The position of the carrier before the GNSS signal is interrupted, thereby interfering with the fusion of pseudo-GNSS data and INS data to obtain error compensation parameters.

[0048] Step S104: Compensate the navigation system according to the error compensation parameters.

[0049] In the technical solution provided in the above step S104 of the present invention, the error of the navigation system after compensation relative to the navigation system before compensation is smaller than the target threshold.

[0050] In this embodiment, after the error compensation parameter is determined in step S103, the navigation system is compensated according to the error compensation parameter.

[0051] Optionally, the error compensation parameters are input into the navigation system for compensation.

[0052] It should be noted that the above embodiments can be implemented by an error compensation device of a navigation system.

[0053] In the above steps S101 to S104 of the present invention, basic data of the navigation system is obtained, wherein the basic data at least includes positioning data and / or motion state data of the mobile device in the navigation system, the positioning data is used to indicate the position of the mobile device, and the motion state data is used to indicate the speed and / or direction of the mobile device; based on the basic data, the error compensation strategy of the navigation system is determined, wherein the error compensation strategy is used to indicate the rules for compensating the navigation system; based on the basic data and the error compensation strategy, the error compensation parameters of the navigation system are determined; according to the error compensation parameters, the navigation system is compensated, wherein the error of the compensated navigation system relative to the error of the navigation system before compensation is less than the target threshold. In other words, the present invention determines the error compensation strategy and error compensation parameters according to the basic data of the navigation system, thereby performing error compensation on the navigation system, thereby solving the technical problem that the navigation system cannot operate stably and achieving the technical effect of improving the stability of the navigation system.

[0054] The above method of this embodiment is further introduced below.

[0055] As an optional implementation method, the error compensation strategy of the navigation system is determined based on basic data, including: in response to valid positioning data, determining that the error compensation strategy of the navigation system is a first compensation strategy; in response to invalid positioning data, determining that the error compensation strategy of the navigation system is a second compensation strategy; wherein the first compensation strategy and the second compensation strategy determine error compensation parameters in different ways.

[0056] In this embodiment, when the positioning data is valid, the error compensation strategy of the navigation system is determined to be the first compensation strategy; when the positioning data is invalid, the error compensation strategy of the navigation system is determined to be the second compensation strategy.

[0057] Optionally, by determining different error compensation strategies, the navigation system errors are fully compensated, thereby improving the stability of the navigation system.

[0058] As an optional implementation method, error compensation parameters of a navigation system are determined based on basic data and an error compensation strategy, including: in response to the error compensation strategy being a first compensation strategy, inputting motion state data into a first compensation model to obtain position increment data, wherein the first compensation model is trained using historical motion state data; and fusing the position increment data with positioning data to obtain error compensation parameters.

[0059] In this embodiment, when the error compensation strategy is the first compensation strategy, the motion state data is input into the first compensation model to obtain position increment data, and the position increment data is fused with the positioning data to obtain error compensation parameters.

[0060] For example, when training the first compensation model, a 15-state vector is used in both the construction of the first compensation model and the experimental analysis, that is, the input of the model can be expressed as the following formula (4):

[0061]

[0062] The position increment data is fused with the positioning data to obtain the error compensation parameters.

[0063] For another example, when GNSS data is available, the first compensation model improves the accuracy of the navigation system by compensating for errors among specific force, angular rate, inertial navigation attitude, and GNSS position increment.

[0064] As an optional implementation method, error compensation parameters of a navigation system are determined based on basic data and an error compensation strategy, including: in response to the error compensation strategy being a second compensation strategy, inputting the positioning data into a second compensation model to obtain pseudo-position data, wherein the second compensation model is trained using historical positioning data; and fusing the pseudo-position data with motion state data to obtain error compensation parameters.

[0065] In this embodiment, when the error compensation strategy is the second compensation strategy, the positioning data is input into the second compensation model to obtain pseudo position data, and the pseudo position data is fused with the motion state data to obtain error compensation parameters.

[0066] For example, when GNSS data is unavailable, the integrated navigation system works under an independent INS system, and the positioning error will continue to diverge over time. Currently, the trained model is used to output a pseudo GNSS signal to correct the navigation system.

[0067] As an optional implementation manner, compensating the navigation system according to the error compensation parameter includes: inputting the error compensation parameter into the navigation system for compensation.

[0068] In this embodiment, the error compensation parameters are input into the navigation system for compensation to improve the accuracy of the navigation system.

[0069] As an optional embodiment, before acquiring basic data of the navigation system, the method further includes: calibrating an inertial sensor in the navigation system.

[0070] In this embodiment, due to manufacturing process and installation errors, the gyroscope and accelerometer have zero bias and scale factor errors, and the inertial sensors in the navigation system need to be calibrated.

[0071] For example, inertial sensors generally include gyroscopes and accelerometers. Due to manufacturing process and installation errors, gyroscopes and accelerometers have zero bias and scale factor errors, which are the root cause of the divergence of positioning errors and need to be calibrated and compensated before solving. The position error equation is expressed as the following formula (5):

[0072]

[0073] Among them, δL, δλ and δh are the latitude, longitude and altitude errors respectively; δv E ,δv N and δv U are the east, north and upward velocity errors respectively; R M and R N Indicates the radius of curvature on the meridian and perpendicular line.

[0074] It should be noted that the above embodiments can be implemented by an error compensation device of a navigation system.

[0075] In this embodiment, basic data of the navigation system is obtained, wherein the basic data at least includes positioning data and / or motion state data of a mobile device in the navigation system, the positioning data is used to indicate the position of the mobile device, and the motion state data is used to indicate the speed and / or direction of the mobile device; based on the basic data, an error compensation strategy of the navigation system is determined, wherein the error compensation strategy is used to indicate the rules for compensating the navigation system; based on the basic data and the error compensation strategy, error compensation parameters of the navigation system are determined; according to the error compensation parameters, the navigation system is compensated, wherein the error of the compensated navigation system relative to the error of the navigation system before compensation is less than the target threshold. That is to say, the present invention determines the error compensation strategy and error compensation parameters according to the basic data of the navigation system, thereby performing error compensation on the navigation system, thereby solving the technical problem that the navigation system cannot operate stably, and achieving the technical effect of improving the stability of the navigation system.

[0076] The technical solution of the embodiment of the present invention is illustrated below in conjunction with preferred implementation modes.

[0077] At present, in the traditional integrated navigation system, the combination of the Global Navigation Satellite System (GNSS) and the Inertial Navigation System (INS) provides high-precision position and attitude estimation for various navigation scenarios. However, GNSS signals are easily interfered by factors such as occlusion and reflection in complex environments, such as urban canyons, densely forested areas, or underground spaces, and even completely interrupted. This signal instability makes it impossible for the system to continuously provide reliable high-precision positioning information.

[0078] In the related art, although INS can maintain the positioning function for a short period of time by relying on inertial sensors, the inherent drift, noise and cumulative error problems of the sensors cause the navigation accuracy to drop rapidly, making it difficult for long-term independent use of INS to meet actual needs. Therefore, there is a technical problem that the navigation system cannot operate stably. At present, no effective solution has been proposed for the above-mentioned technical problem that the navigation system cannot operate stably.

[0079] However, the embodiment of the present invention proposes a GNSS / INS combined navigation system error compensation method based on AT-LSTM neural network, obtains basic data of the navigation system, wherein the basic data may include GNSS data and INS data; trains the model using historical basic data; according to different situations, that is, GNSS signal available and GNSS signal unavailable, inputs different parameters into different compensation models, obtains error compensation parameters, and compensates with the navigation system according to the error compensation parameters. The technical problem that the navigation system cannot operate stably is solved, and the technical effect of improving the stability of the navigation system is achieved.

[0080] The embodiments of the present invention are further described below.

[0081] Figure 2 is a schematic diagram of a GNSS / INS integrated navigation error compensation method according to an embodiment of the present invention, such as Figure 2 As shown in Figure 1, inertial sensors generally include gyroscopes and accelerometers. Due to manufacturing process and installation errors, gyroscopes and accelerometers have zero bias and scale factor errors, which are the root causes of positioning error divergence. Therefore, calibration and compensation are required before solving.

[0082] In this embodiment, the position error equation can be expressed as the aforementioned formula (5), which will not be described again here.

[0083] Alternatively, the GNSS data is data obtained by receiving satellite signals through a global navigation satellite system (GNSS) to obtain position, speed and time information.

[0084] Optionally, INS data is obtained by an inertial navigation system (INS) to obtain the position, speed and attitude information of an aircraft, ship or vehicle. The INS system measures the motion state of the aircraft through sensors such as accelerometers, gyroscopes and magnetometers to achieve navigation and positioning.

[0085] Optionally, GNSS data and INS data are often used in combination to provide more accurate and reliable navigation information. The INS system can provide stable position and attitude information, while the GNSS system can provide updated position information. By fusing these two types of data, a higher-precision navigation solution can be obtained.

[0086] Optionally, an inertial sensor is a sensor that can measure the motion state of an object in space. It determines the motion trajectory and attitude of an object by measuring the acceleration and angular velocity of the object. Common inertial sensors include accelerometers and gyroscopes, which are commonly used in navigation systems, aircraft, automobiles, and virtual reality. The working principle of an inertial sensor is to use the inertial characteristics of an object to measure its motion state, so it can accurately determine the position and attitude of an object in an environment without a GPS signal.

[0087] Figure 3 is a schematic diagram of a GNSS / INS loosely coupled structure and a Kalman filtering process according to an embodiment of the present invention, such as Figure 3 As shown in Figure 1, the GNSS / INS integrated navigation system can be divided into three types: loose coupling, tight coupling and ultra-tight coupling. Kalman filtering is the most commonly used filtering algorithm in the GNSS / INS integrated navigation system. Its calculation process is a process of continuous prediction (time update) and correction (measurement update), which facilitates real-time processing of observation results.

[0088] In this embodiment, the state equation and measurement equation of the discrete Kalman filter at time k are expressed as the following formula (6):

[0089]

[0090] Among them, X k represents the state vector at time k, Φ k / k-1 represents the state transfer matrix, X k-1 represents the state vector at time k-1, Γ k-1 represents the noise matrix; W k-1 represents motion noise, which obeys Gaussian distribution N(0, Qk-1), z k represents the measured value at time k, H k represents the measurement matrix, V k represents the measurement noise.

[0091] Optionally, the Kalman filter is divided into two parts: time update and metric update. Its calculation is a process of continuous prediction and correction, and its state prediction equation is shown in the following formula (7):

[0092]

[0093] Optionally, the state prediction variance is shown in the following formula (8):

[0094]

[0095] Optionally, the Kalman gain is as shown in the following formula (9):

[0096]

[0097] Optionally, the state estimation is shown in the following formula (10):

[0098]

[0099] Optionally, the error variance is as shown in the following formula (11):

[0100] P k =(IK k H k ) k / k-1 (11)

[0101] Optionally, a 15-state vector is used in both model construction and experimental analysis, which can be expressed as the aforementioned formula (4), which will not be described in detail here.

[0102] Optionally, it can be seen from the INS update algorithm that the INS update algorithm is a process of continuously integrating and increasing the IMU (Inertial Measurement Unit) output. A relationship model between INS information and GNSS position increment is established. The position increment can be expressed in the quadratic integral form of the specific force equation as the aforementioned formula (2). The input and output of the model are expressed as the aforementioned formula (1), which will not be repeated here.

[0103] Optionally, an IMU is a device that integrates multiple inertial sensors to measure the acceleration, angular velocity, and orientation of an object. A typical IMU includes a three-axis accelerometer, a three-axis gyroscope, and a three-axis magnetometer. These sensors can provide information about the position, orientation, and motion state of an object in space.

[0104] Optionally, IMU data is usually provided in digital format and can be transferred to a microcontroller or computer via a serial interface (such as SPI or I2C) for processing and analysis. This data can be used for navigation, attitude control, motion detection and other application areas.

[0105] Optionally, the processing and analysis of IMU data needs to consider techniques such as calibration between sensors, data fusion and filtering to ensure accurate and reliable results. IMUs are also often used in conjunction with other sensors (e.g., GPS, vision sensors) to improve the accuracy and stability of position and orientation estimates.

[0106] Optionally, Kalman filtering is an optimization algorithm for estimating the state of a system. It combines information from predicted values ​​and observed values ​​to optimize the state estimate by minimizing the error between the predicted values ​​and the observed values. Kalman filtering is applicable to dynamic systems and can effectively handle noise and uncertainty, improving the accuracy and stability of state estimation. In practical applications, Kalman filtering is often used in aerospace, navigation, robotics, and unmanned driving.

[0107] Figure 4 is a schematic diagram of a GNSS / INS integrated navigation system model training phase according to an embodiment of the present invention, such as Figure 4 As shown in Figure 1, the combined navigation error compensation method based on AT-LSTM is divided into two modes. When GNSS is available, the model is trained.

[0108] In this embodiment, IMU data, namely specific force, angular velocity and INS attitude information, are used as input of the model during training, and GNSS position increment is used as output of the model.

[0109] Optionally, the AT-LSTM neural network (Attention-based Long Short-Term Memory) is a Long Short-Term Memory network (LSTM) based on the attention mechanism for processing sequence data. In the traditional LSTM network, the model learns the representation of the entire input sequence, while the AT-LSTM introduces an attention mechanism that allows the model to focus on different parts of the input sequence at each time step.

[0110] Optionally, AT-LSTM calculates an attention weight vector at each time step to weight different parts of the input sequence, thereby adjusting the model's attention to different parts. This allows the model to better capture important information in the input sequence and improve the model's performance and generalization ability.

[0111] Alternatively, the AT-LSTM neural network has achieved good results in natural language processing, speech recognition, time series prediction and other fields, and has become one of the important models in deep learning. By introducing the attention mechanism, AT-LSTM can better process long sequence data and achieve better performance when processing complex tasks.

[0112] Figure 5 is a schematic diagram of a GNSS / INS integrated navigation system model prediction stage according to an embodiment of the present invention, such as Figure 5 As shown in Figure 1, when the GNSS signal is unavailable, the integrated navigation system works under an independent INS system, and the positioning error will continue to diverge over time. At present, the trained model is used to output a pseudo GNSS signal to correct the INS system.

[0113] In this embodiment, starting from the first epoch after GNSS is unavailable, the position increment (+PGNSS) output by the model is accumulated to obtain the pseudo GNSS position of each epoch, as shown in the above formula (3), which will not be repeated here. The pseudo GNSS position is integrated into the Kalman filter, that is, the GNSS information and the IMU information are fused, and accurate information is output to achieve error compensation for the integrated navigation system.

[0114] Optionally, the present invention proposes an error compensation method based on a long short-term memory (LSTM) neural network integrated attention mechanism (AT-LSTM) for a GNSS / INS integrated navigation system. When a GNSS signal is available, the model improves the accuracy of the navigation system by compensating for the errors between specific force, angular rate, inertial navigation attitude, and GNSS position increment. When the GNSS signal is interrupted, the error compensation model can output a pseudo-GNSS signal to compensate the integrated navigation system and suppress the divergence of the positioning error. This method significantly improves the positioning accuracy of the UAV in the event of a GNSS signal interruption.

[0115] In this embodiment, basic data of the navigation system is obtained, wherein the basic data may include GNSS data and INS data; the model is trained using historical basic data; different parameters are input into different compensation models according to different situations, i.e., when the GNSS signal is available and when the GNSS signal is unavailable, to obtain error compensation parameters, and compensation is performed with the navigation system according to the error compensation parameters. The technical problem that the navigation system cannot operate stably is solved, and the technical effect of improving the stability of the navigation system is achieved.

[0116] According to an embodiment of the present invention, there is also provided an error compensation device for a navigation system. It should be noted that the error compensation device for a navigation system can be used to execute the error compensation method for a navigation system in the method embodiment.

[0117] Figure 6 is a schematic diagram of an error compensation device for a navigation system according to an embodiment of the present invention. Figure 6 As shown, the error compensation device 600 of the navigation system may include: an acquisition unit 601 , a first determination unit 602 , a second determination unit 603 and a compensation unit 604 .

[0118] The acquisition unit 601 is used to acquire basic data of the navigation system, wherein the basic data at least includes positioning data and / or motion status data, the positioning data is used to indicate the position of the mobile device in the navigation system, and the motion status data is used to indicate the speed and / or direction of the mobile device in the navigation system.

[0119] The first determining unit 602 is used to determine an error compensation strategy for the navigation system based on basic data, wherein the error compensation strategy is used to indicate a rule for compensating the navigation system.

[0120] The second determining unit 603 is used to determine the error compensation parameters of the navigation system based on the basic data and the error compensation strategy.

[0121] The compensation unit 604 is used to compensate the error of the navigation system according to the error compensation parameter, wherein the error of the navigation system after compensation relative to the navigation system before compensation is less than a target threshold.

[0122] Optionally, the first determination unit 602 may include: a first determination module, used to determine that the error compensation strategy of the navigation system is a first compensation strategy in response to valid positioning data; a second determination module, used to determine that the error compensation strategy of the navigation system is a second compensation strategy in response to invalid positioning data; wherein the first compensation strategy and the second compensation strategy determine error compensation parameters in different ways.

[0123] Optionally, the second determination unit 603 may include: a first input module, used to input the motion state data into the first compensation model in response to the error compensation strategy being the first compensation strategy, to obtain position increment data, wherein the first compensation model is obtained by training using historical motion state data; a first fusion module, used to fuse the position increment data with the positioning data to obtain error compensation parameters.

[0124] Optionally, the second determination unit 603 may include: a second input module, used to input the positioning data into a second compensation model in response to the error compensation strategy being the second compensation strategy, to obtain pseudo-position data, wherein the second compensation model is trained using historical positioning data; a second fusion module, used to fuse the pseudo-position data with the motion state data to obtain error compensation parameters.

[0125] Optionally, the compensation unit 604 may include: a third input module, used to input the error compensation parameter into the navigation system for compensation.

[0126] Optionally, the error compensation device 600 of the navigation system may further include: a calibration module, used to calibrate the inertial sensor in the navigation system.

[0127] In this embodiment, basic data of the navigation system is obtained, wherein the basic data at least includes positioning data and / or motion state data of a mobile device in the navigation system, the positioning data is used to indicate the position of the mobile device, and the motion state data is used to indicate the speed and / or direction of the mobile device; based on the basic data, an error compensation strategy of the navigation system is determined, wherein the error compensation strategy is used to indicate the rules for compensating the navigation system; based on the basic data and the error compensation strategy, error compensation parameters of the navigation system are determined; according to the error compensation parameters, the navigation system is compensated, wherein the error of the compensated navigation system relative to the error of the navigation system before compensation is less than the target threshold. That is to say, the present invention determines the error compensation strategy and error compensation parameters according to the basic data of the navigation system, thereby performing error compensation on the navigation system, thereby solving the technical problem that the navigation system cannot operate stably, and achieving the technical effect of improving the stability of the navigation system.

[0128] According to an embodiment of the present invention, there is further provided a computer-readable storage medium, the storage medium comprising a stored program, wherein the program executes the error compensation method of the navigation system in the method embodiment.

[0129] According to an embodiment of the present invention, a processor is further provided. The processor is used to run a program, wherein the error compensation method of the navigation system in the method embodiment is executed when the program is running.

[0130] According to an embodiment of the present invention, a computer program product is further provided. The computer program product includes computer instructions. When the computer instructions are executed by a processor, the error compensation method of the navigation system in the method embodiment is implemented.

[0131] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0132] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0133] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0134] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed over multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0135] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0136] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent functional component, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software functional component, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk, etc., which can store program codes.

[0137] The above are only preferred embodiments of the present invention. It should be pointed out that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A navigation system error compensation method, characterized in that: include: Acquire basic data of the navigation system, wherein the basic data at least includes positioning data and / or motion state data of the mobile device in the navigation system, the positioning data is used to indicate the position of the mobile device, and the motion state data is used to indicate the speed and / or direction of the mobile device; Determining an error compensation strategy for the navigation system based on the basic data, wherein the error compensation strategy is used to indicate a rule for compensating the navigation system; Determining error compensation parameters of the navigation system based on the basic data and the error compensation strategy; The navigation system is compensated according to the error compensation parameter, wherein an error of the navigation system after compensation relative to the navigation system before compensation is smaller than a target threshold.

2. The method according to claim 1, characterized in that Determining an error compensation strategy of the navigation system based on the basic data includes: In response to the positioning data being valid, determining that the error compensation strategy of the navigation system is a first compensation strategy; In response to the positioning data being invalid, determining that the error compensation strategy of the navigation system is a second compensation strategy; wherein the first compensation strategy and the second compensation strategy determine the error compensation parameters in different ways.

3. The method according to claim 1, characterized in that: Determining error compensation parameters of the navigation system based on the basic data and the error compensation strategy includes: In response to the error compensation strategy being a first compensation strategy, the motion state data is input into a first compensation model to obtain position increment data, wherein the first compensation model is obtained by training using historical motion state data; The position increment data is fused with the positioning data to obtain the error compensation parameter.

4. The method according to claim 1, characterized in that Determining error compensation parameters of the navigation system based on the basic data and the error compensation strategy includes: In response to the error compensation strategy being a second compensation strategy, inputting the positioning data into a second compensation model to obtain pseudo position data, wherein the second compensation model is obtained by training using historical positioning data; The pseudo position data is fused with the motion state data to obtain the error compensation parameter.

5. The method according to claim 1, characterized in that Compensating the navigation system according to the error compensation parameter includes: The error compensation parameters are input into the navigation system for compensation.

6. The method according to claim 1, characterized in that Before acquiring basic data of the navigation system, the method further includes: An inertial sensor in the navigation system is calibrated.

7. A navigation system error compensation device, characterized in that: include: an acquisition unit, configured to acquire basic data of a navigation system, wherein the basic data at least includes positioning data and / or motion state data, the positioning data being used to indicate a position of a mobile device in the navigation system, and the motion state data being used to indicate a speed and / or direction of the mobile device in the navigation system; A first determining unit, configured to determine an error compensation strategy of the navigation system based on the basic data, wherein the error compensation strategy is used to indicate a rule for compensating the navigation system; A second determining unit, configured to determine an error compensation parameter of the navigation system based on the basic data and the error compensation strategy; A compensation unit is used to compensate for the error of the navigation system according to the error compensation parameter, wherein the error of the navigation system after compensation relative to the navigation system before compensation is less than a target threshold.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed by a processor, the device where the storage medium is located is controlled to execute the method according to any one of claims 1 to 6.

9. A processor, characterized in that: The processor is used to run a program, wherein the program executes the method according to any one of claims 1 to 6 when running.

10. A computer program product, characterized in that The computer program product comprises computer instructions, which implement the method according to any one of claims 1 to 6 when executed by a processor.

Images