Method, device, equipment, medium and automatic driving vehicle for determining navigation state information

Abstract

The present disclosure provides a method, device, equipment, medium and autonomous vehicle for determining navigation state information, relates to the technical field of navigation, and particularly relates to the technical field of autonomous driving and artificial intelligence. The specific implementation scheme comprises: performing forward Kalman filtering on the measurement data of GNSS and the measurement data of IMU in N+1 time points, and solving to obtain the forward filtering variance and the forward state value corresponding to each time point respectively; performing smoothing processing on the forward filtering variance respectively; performing backward Kalman filtering on the measurement data of GNSS and the measurement data of IMU, and solving to obtain the backward filtering variance and the backward state value corresponding to each time point respectively; performing smoothing processing on the backward filtering variance respectively; and fusing the forward state value and the backward state value according to the smoothed forward filtering variance and the smoothed backward filtering variance, to obtain state information. Thus, the trajectory of each state information obtained by fusion is smoother, and the state information is more accurate.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the field of navigation technology, in particular to the field of autonomous driving and artificial intelligence. BACKGROUND

[0002] The positioning and perception of an autonomous vehicle cannot be separated from high-precision maps and positioning maps. The production of online high-precision maps / positioning maps relies on high-precision initial state information. Based on high-precision / high-availability initial state information, the efficiency of high-precision map / positioning map production can be effectively improved. The high-precision initial state information can usually be obtained by post-processing and solving the measurement data of a global navigation satellite system (GNSS) and an inertial measurement unit (IMU). SUMMARY

[0003] The present disclosure provides a method, device, equipment, medium and autonomous vehicle for determining state information, and the determined state information has higher precision.

[0004] According to a first aspect of the present disclosure, a method for determining state information is provided, which comprises: performing forward Kalman filtering on the measurement data of a global navigation satellite system (GNSS) and the measurement data of an inertial measurement unit (IMU) within N+1 time points, to obtain the forward filtering variance and the forward state value corresponding to each time point respectively, N being a positive integer greater than or equal to 1; performing smoothing processing on the forward filtering variance respectively, to obtain the smoothed forward filtering variance corresponding to each time point respectively; performing backward Kalman filtering on the measurement data of the GNSS and the measurement data of the IMU, to obtain the backward filtering variance and the backward state value corresponding to each time point respectively; performing smoothing processing on the backward filtering variance respectively, to obtain the smoothed backward filtering variance corresponding to each time point respectively; and fusing the forward state value and the backward state value according to the smoothed forward filtering variance and the smoothed backward filtering variance, to obtain the state information.

[0005] According to a second aspect of the present disclosure, there is provided a device for determining state information, the device comprising: a forward filtering module configured to perform forward Kalman filtering on measurement data of a global navigation satellite system (GNSS) and measurement data of an inertial measurement unit (IMU) at N+1 time instants, to obtain a forward filtering variance and a forward state value corresponding to each time instant, respectively, N being a positive integer greater than or equal to 1; a forward smoothing module configured to perform smoothing processing on the forward filtering variance to obtain a smoothed forward filtering variance corresponding to each time instant, respectively; a backward filtering module configured to perform backward Kalman filtering on the measurement data of the GNSS and the measurement data of the IMU to obtain a backward filtering variance and a backward state value corresponding to each time instant, respectively; a backward smoothing module configured to perform smoothing processing on the backward filtering variance to obtain a smoothed backward filtering variance corresponding to each time instant, respectively; and a fusion module configured to fuse the forward state value and the backward state value according to the smoothed forward filtering variance and the smoothed backward filtering variance to obtain the state information.

[0006] According to a third aspect of the present disclosure, there is provided an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to the first aspect.

[0007] According to a fourth aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method according to the first aspect.

[0008] According to a fifth aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the method according to the first aspect.

[0009] According to a sixth aspect of the present disclosure, there is provided an autonomous vehicle comprising the electronic device according to the third aspect of the present disclosure.

[0010] The present disclosure can increase the smoothing processing on the filtering variance in the forward filtering and the backward filtering, respectively, so that the trajectory of the state information obtained by fusing the forward filtering result and the backward filtering result according to the smoothed filtering variance is smoother, and the accuracy of the state information is higher, which is beneficial to the subsequent high-precision map / positioning map making according to the obtained state information.

[0011] It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0012] The accompanying drawings are used to better understand the present scheme, and do not constitute a limitation on the present disclosure. Among them:

[0013] Figure 1 The flowchart of the method for determining state information provided by the embodiments of the present disclosure is shown;

[0014] Figure 2 The flowchart of a method for implementing S101 in the method for determining state information provided by the embodiments of the present disclosure is shown;

[0015] Figure 3 The flowchart of a method for implementing S103 in the method for determining state information provided by the embodiments of the present disclosure is shown;

[0016] Figure 4 The composition diagram of the device for determining state information provided by the embodiments of the present disclosure is shown;

[0017] Figure 5 The schematic block diagram of an example electronic device 500 that can be used to implement the embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0018] The exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to help understanding, and should be considered only as exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Also, in order to be clear and concise, the description below omits the description of well-known functions and structures.

[0019] The method for determining state information (or navigation state information) and the device for determining state information provided by the present disclosure are suitable for determining the state information of a collection terminal, so as to draw a high-precision map / positioning map according to the state information. The method for determining state information provided by the present disclosure can be executed by the device for determining state information, which can be implemented by software and / or hardware, and is specifically configured in an electronic device, which can be a collection terminal and / or other computing devices associated with the collection terminal, such as a positioning system (or positioning module), a server, etc. For example, the collection terminal can be an electronic device with positioning and navigation functions, and can also be an autonomous vehicle, etc., which is not limited here.

[0020] The method for determining state information provided by the present disclosure is described in detail below.

[0021] The positioning and perception of an autonomous vehicle cannot be separated from high-precision maps and positioning maps. The production of online high-precision maps / positioning maps relies on high-precision initial state information. Based on high-precision / high-availability initial state information, the efficiency of high-precision map / positioning map production can be effectively improved. The high-precision initial state information can usually be obtained by post-processing the measurement data of a global navigation satellite system (GNSS) / inertial measurement unit (IMU).

[0022] For example, a forward (i.e., forward) and a backward (i.e., backward) Kalman filter can be established, each of which performs integrated navigation calculation to obtain the results of the respective filters, and finally the results of the two are combined to output the final result (i.e., state information) by fusing the respective filter variances.

[0023] However, when the innovation of the GNSS measurement and the predicted value is large, according to the measurement update principle of the Kalman filter, the filter variance weight will also have a large jump during the update, that is, the filter covariance is affected by the jump of the measurement filter variance matrix, and the forward and backward filter variance matrices will fluctuate. When the filter variances calculated by the forward and backward filters are directly used for fusion in the final fusion stage, the curve trajectory formed by the state information will have a local non-smooth phenomenon, and the accuracy is low, which is not conducive to subsequent high-precision map / positioning map production based on the obtained state information.

[0024] To this end, the present application provides a method for determining state information, which comprises: performing forward Kalman filtering on the measurement data of a global navigation satellite system (GNSS) and the measurement data of an inertial measurement unit (IMU) at N+1 time points to obtain the forward filter variances and the forward state values corresponding to each time point, respectively. Wherein, N is a positive integer greater than or equal to 1. The forward filter variances are respectively smoothed to obtain the smoothed forward filter variances corresponding to each time point. The measurement data of the GNSS and the measurement data of the IMU are subjected to backward Kalman filtering to obtain the backward filter variances and the backward state values corresponding to each time point, respectively. The backward filter variances are respectively smoothed to obtain the smoothed backward filter variances corresponding to each time point. The forward state values and the backward state values are fused according to the smoothed forward filter variances and the smoothed backward filter variances to obtain the state information.

[0025] The present disclosure can make the trajectory of each state information obtained by fusing the forward and backward solving results according to the smoothed filter variances more smooth, and the state information more accurate, which is beneficial to subsequent high-precision map / positioning map making according to the obtained state information, by smoothing the filter variances in the forward (i.e., forward) filtering solving and the backward (i.e., backward) filtering solving, respectively.

[0026] In some embodiments, the alignment method for determining state information provided by the present disclosure can be applied to a terminal with positioning and navigation functions, such as a smart phone, a personal positioning terminal, a tablet computer, and the like, so that the electronic device can determine its own state information according to the GNSS measurement data and IMU measurement data collected by the electronic device. Alternatively, the method can also be applied to an autonomous vehicle, so that the autonomous vehicle can determine its own state information according to the GNSS measurement data and IMU measurement data collected by the positioning system of the autonomous vehicle. The state information can include position, velocity, attitude, and the like. Alternatively, the method can also be applied to a server (such as a cloud server) or other computing devices to process the GNSS measurement data and IMU measurement data collected by the collection terminal, so as to obtain the state information of the collection terminal, thereby facilitating subsequent high-precision map / positioning map making according to the state information. The collection terminal can be a device provided with GNSS and IMU, or an autonomous vehicle.

[0027] Figure 1 A flowchart of the method for determining state information provided by the embodiments of the present disclosure is shown in FIG. 1. Figure 1 As shown in FIG. 1, the method can include the following S101-S105.

[0028] S101, performing forward Kalman filtering on the measurement data of a global navigation satellite system (GNSS) and the measurement data of an inertial measurement unit (IMU) within N+1 time points, to obtain the forward filter variance and the forward state value corresponding to each time point, respectively, N being a positive integer greater than or equal to 1.

[0029] The GNSS measurement data and the IMU measurement data are respectively the data obtained by the GNSS positioning measurement on the corresponding terminal (such as the above-mentioned terminal with positioning and navigation functions, the collection terminal, and the autonomous vehicle, etc.) and the measurement data related to the motion of the corresponding terminal collected by the IMU.

[0030] The N+1 time points can be set according to the period of collecting the IMU measurement data by the corresponding terminal, so that there is IMU measurement data collected by the corresponding terminal corresponding to each time point. At this time, according to the measurement period of the GNSS, only part of the time points in the N+1 time points can correspond to the GNSS measurement data, and part of the time points can not have corresponding GNSS measurement data.

[0031] Optionally, the forward state value can comprise a parameter value of position, velocity and attitude related parameters calculated according to the forward Kalman filtering.

[0032] As an example, the forward Kalman filtering on the GNSS measurement data and the IMU measurement data can be performed by a forward Kalman filter. Optionally, a forward Kalman filter can be established before this step to perform the forward Kalman filtering on the GNSS measurement data and the IMU measurement data.

[0033] S102, respectively smoothing the forward filtering variances to obtain the smoothed forward filtering variances corresponding to respective time instants.

[0034] The manner of respectively smoothing the forward filtering variances can be to smooth the respective forward filtering variances to be smoothed according to the forward filtering variances to be smoothed and all the forward filtering variances before the time instant corresponding to the forward filtering variances to be smoothed.

[0035] For example, taking N+1 time instants as the Kth time instant to the K+N time instant, the forward filtering variances of respective time instants are P k , P k+1 , P k+2 ……P k+N , then the smoothed forward filtering variance of the K+N time instant is which can be calculated according to the following formula:

[0036]

[0037] wherein the smoothed value of the forward filtering variance of the Kth time instant is unchanged.

[0038] Thus, the forward filtering variances of the N+1 time instants can be smoothed according to the above formula to obtain the smoothed forward filtering variances.

[0039] S103, performing backward Kalman filtering on the GNSS measurement data and the IMU measurement data to calculate the backward filtering variances and the backward state values corresponding to respective time instants.

[0040] Optionally, the backward state value can comprise a parameter value of position, velocity and attitude related parameters calculated according to the backward Kalman filtering.

[0041] As an example, the backward Kalman filtering on the GNSS measurement data and the IMU measurement data can be performed by a backward Kalman filter. Optionally, a backward Kalman filter can be established before this step to perform the backward Kalman filtering on the GNSS measurement data and the IMU measurement data.

[0042] S104, respectively smooth the backward filtering variances to obtain the smoothed backward filtering variances corresponding to the respective time points.

[0043] Optionally, the manner of smoothing the backward filtering variances can refer to the description of the forward filtering variances in S102, which is not limited here.

[0044] S105, fuse the forward state values and the backward state values according to the smoothed forward filtering variances and the smoothed backward filtering variances to obtain the state information.

[0045] For example, when the forward state values corresponding to the respective time points, the smoothed forward filtering variances, the backward state values, and the smoothed backward filtering variances are obtained, the forward state values and the backward state values at the respective time points can be fused according to the following formula to obtain the final state information:

[0046]

[0047]

[0048] wherein, is the smoothed forward filtering variance corresponding to the respective time point, is the forward state value corresponding to the respective time point, is the smoothed backward filtering variance corresponding to the respective time point, is the backward state value corresponding to the respective time point, is the final fused state information.

[0049] In this way, the state information corresponding to each time point in N+1 time points can be calculated according to the above formula.

[0050] Optionally, Figure 2 is a flowchart of a method for implementing S101 in the method for determining state information provided by the present disclosure.

[0051] As Figure 2 shown, the method can include the following S201-S203.

[0052] S201, forward Kalman filtering recursion is performed according to the measurement data of the IMU at each time point to obtain the forward prediction filtering variance and the forward prediction state value corresponding to the respective time points.

[0053] For example, the forward Kalman filtering recursion can be performed according to the measurement data of the IMU based on the forward Kalman filtering recursion formula to obtain the forward prediction filtering variance and the forward prediction state value corresponding to the respective time points.

[0054] For example, the estimated state of the forward Kalman filter at time t is denoted as δx.

[0055]

[0056] where δp represents the position error, δv represents the velocity error, represents the attitude error, δa b represents the accelerometer bias error, δg b represents the gyroscope bias error.

[0057] For example, the estimated state of the forward Kalman filter at time t is denoted as δx. k Thus, when the measurement data of the IMU at time K+1 is input into the Kalman filter, the forward prediction filter variance and the forward prediction state value at time K+1 can be obtained by recursion according to the following recursion equation:

[0058]

[0059]

[0060] wherein, is the forward prediction variance matrix at time K+1 (i.e., the forward prediction filter variance), is the forward prediction state matrix at time K+1 (i.e., the forward prediction state value). Φ k+1，k is the state transition matrix from time k to time k+1, Γ(k) is the state noise driving matrix at time k, and Q is the system noise matrix, is the forward prediction state matrix at time k-1 to time k (i.e., the forward prediction state value), and both are known parameters.

[0061] Thus, the forward prediction filter variance and the forward prediction state value at each time can be recursively obtained according to the measurement data of the IMU at the corresponding time according to the above recursion equation.

[0062] S202, updating the forward prediction filter variance and the forward prediction state value at the time corresponding to each GNSS measurement data according to the GNSS measurement data.

[0063] For example, the forward prediction filter variance and the forward prediction state value at the corresponding time can be updated according to the GNSS measurement data based on the forward Kalman filter update equation.

[0064] For example, based on the description in S201, taking the corresponding GNSS measurement data at K+1 time as an example, the forward prediction filtering variance and the forward prediction state value at K+1 time can be updated according to the following formula:

[0065]

[0066]

[0067]

[0068]

[0069] wherein is the updated forward prediction state value at K+1 time, P k+1 is the updated forward prediction filtering variance matrix (i.e., the forward prediction filtering variance) at K+1 time. K k+1 is the gain matrix, is the measurement matrix in the GNSS measurement data, R is the variance weight matrix of the GNSS measurement data, V z (k+1) is the innovation sequence, Z(k+1) is the observation value in the GNSS measurement data, is the forward prediction state matrix (i.e., the forward prediction state value) at k+1 time, and both are known values.

[0070] In this way, the forward prediction filtering variance and the forward prediction state value recursively obtained at the corresponding time can be updated according to the above updating equation according to the GNSS measurement data at the corresponding time.

[0071] S203, for each time, if the corresponding forward prediction filtering variance and the forward prediction state value are not updated, the forward prediction filtering variance and the forward prediction state value are taken as the corresponding forward filtering variance and the forward state value, and if the corresponding forward prediction filtering variance and the forward prediction state value are updated, the updated forward prediction filtering variance and the forward prediction state value are taken as the corresponding forward filtering variance and the forward state value.

[0072] For example, based on the foregoing descriptions of S201 and S202, the updated forward prediction filtering variance and the forward prediction state value corresponding to K time to K+N time can be taken as the corresponding forward filtering variance and the forward state value at the corresponding time. When the forward prediction filtering variance and the forward prediction state value at the corresponding time are not updated according to S202, the forward prediction filtering variance and the forward prediction state value corresponding to the time obtained by S201 are taken as the corresponding forward filtering variance and the forward state value.

[0073] For example, the forward prediction filter variance and the forward prediction state value at K+3 time are updated according to S202, and the forward prediction filter variance and the forward prediction state value at K+3 time updated by S202 can be taken as the forward filter variance and the forward state value thereof. The forward prediction filter variance and the forward prediction state value at K+5 time are not updated according to S202, and the forward prediction filter variance and the forward prediction state value at K+5 time obtained by S201 can be taken as the forward filter variance and the forward state value thereof.

[0074] In this way, the forward filter variance and the forward state value at each time can be predicted according to the Kalman filter recursion formula, and the forward filter variance and the forward state value predicted at the corresponding time can be updated according to the measurement data of the GNSS, so that the forward filter variance and the forward state value corresponding to each time can be determined more accurately.

[0075] Optionally, Figure 3 A flowchart of a method for implementing S103 in the method for determining state information provided by the present disclosure is shown.

[0076] As Figure 3 shown, the method can include the following S301-S303.

[0077] S301, backward Kalman filter recursion is performed according to the measurement data of the IMU at each time to obtain the backward prediction filter variance and the backward prediction state value corresponding to each time respectively.

[0078] S302, the backward prediction filter variance and the backward prediction state value at the time corresponding to each measurement data of the GNSS are updated according to the measurement data of the GNSS.

[0079] S303, for each time, if the corresponding backward prediction filter variance and the backward prediction state value are not updated, the backward prediction filter variance and the backward prediction state value are taken as the corresponding backward filter variance and the backward state value thereof, and if the corresponding backward prediction filter variance and the backward prediction state value are updated, the updated backward prediction filter variance and the backward prediction state value are taken as the corresponding backward filter variance and the backward state value thereof.

[0080] It should be noted that the specific implementation of S301-S303 is similar to S201-S203 in the method as Figure 2 shown, and the only difference is that the recursion is backward Kalman recursion (i.e., the prediction filter variance and the prediction state value are recursively propagated and updated from K+N time to K time for K time to K+N time). For details, refer to the related description in the method as Figure 2 shown, which will not be described here.

[0081] Thus, the backward filtering variance and the backward state value at each time can be predicted according to the Kalman filtering recursion formula, and the backward filtering variance and the backward state value predicted at the corresponding time can be updated according to the measurement data of the GNSS, so that the corresponding backward filtering variance and the backward state value at each time can be determined more accurately.

[0082] Optionally, in the embodiment of the present application, the method for determining state information can further include the steps of acquiring the measurement data of the GNSS and the measurement data of the IMU at N+1 times, respectively, which is not limited here. For example, based on the description of S101, the measurement data of the GNSS and the measurement data of the IMU collected by the terminal can be acquired from the terminal first. Alternatively, the measurement data of the GNSS and the measurement data of the IMU can also be acquired from the GNSS and the IMU of the autonomous vehicle or the terminal with positioning and navigation, etc. Thus, the measurement data of the GNSS and the measurement data of the IMU collected by the corresponding terminal can be acquired by the external computing device, so as to determine the state information of the corresponding terminal or the autonomous vehicle by calculating according to the method of the present application, thereby improving the calculation efficiency by improving the computing power.

[0083] In the exemplary embodiment, the present disclosure also provides a device for determining state information, which can be used to implement the method for determining state information as described in the foregoing embodiments.

[0084] Figure 4 The device for determining state information provided by the present disclosure is shown in the composition schematic diagram.

[0085] As shown in Figure 4 , the device can include:

[0086] The forward filtering module 401 is configured to perform forward Kalman filtering on the measurement data of the global navigation satellite system (GNSS) and the measurement data of the inertial measurement unit (IMU) at N+1 times, and calculate the corresponding forward filtering variance and forward state value at each time, where N is a positive integer greater than or equal to 1.

[0087] The forward smoothing module 402 is configured to perform smoothing processing on the forward filtering variance, respectively, to obtain the smoothed forward filtering variance corresponding to each time.

[0088] The backward filtering module 403 is configured to perform backward Kalman filtering on the measurement data of the GNSS and the measurement data of the IMU, and calculate the corresponding backward filtering variance and backward state value at each time.

[0089] The backward smoothing module 404 is configured to perform smoothing processing on the backward filtering variance, respectively, to obtain the smoothed backward filtering variance corresponding to each time.

[0090] fusing the forward state value and the backward state value according to the smoothed forward filter variance and the smoothed backward filter variance, to obtain state information.

[0091] In some embodiments, the forward filtering module 401 is specifically configured to perform forward Kalman filtering recursion according to the measurement data of the IMU at each time point, to obtain a forward predicted filter variance and a forward predicted state value corresponding to each time point respectively; update the forward predicted filter variance and the forward predicted state value corresponding to each time point according to the measurement data of the GNSS; for each time point, if the corresponding forward predicted filter variance and forward predicted state value are not updated, the forward predicted filter variance and the forward predicted state value are taken as the forward filter variance and the forward state value corresponding to the time point, and if the corresponding forward predicted filter variance and forward predicted state value are updated, the updated forward predicted filter variance and forward predicted state value are taken as the forward filter variance and the forward state value corresponding to the time point.

[0092] In some embodiments, the backward filtering module 403 is specifically configured to perform backward Kalman filtering recursion according to the measurement data of the IMU at each time point, to obtain a backward predicted filter variance and a backward predicted state value corresponding to each time point respectively; update the backward predicted filter variance and the backward predicted state value corresponding to each time point according to the measurement data of the GNSS; for each time point, if the corresponding backward predicted filter variance and backward predicted state value are not updated, the backward predicted filter variance and the backward predicted state value are taken as the backward filter variance and the backward state value corresponding to the time point, and if the corresponding backward predicted filter variance and backward predicted state value are updated, the updated backward predicted filter variance and backward predicted state value are taken as the backward filter variance and the backward state value corresponding to the time point.

[0093] In some embodiments, the device further comprises an acquisition module 406 configured to acquire the measurement data of the GNSS and the measurement data of the IMU at N+1 time points respectively.

[0094] In the technical solution of the present disclosure, the acquisition, storage and application of user personal information comply with relevant laws and regulations and do not violate public order and good customs.

[0095] According to the embodiments of the present disclosure, the present disclosure further provides an electronic device, a readable storage medium, a computer program product and an autonomous vehicle.

[0096] In an exemplary embodiment, an electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method as described in the above embodiments.

[0097] In an exemplary embodiment, the readable storage medium may be a non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the method described in the above embodiments.

[0098] In an exemplary embodiment, the computer program product includes a computer program that, when executed by a processor, implements the method described in the above embodiments.

[0099] Figure 5 A schematic block diagram of an example electronic device 500 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as in-vehicle computers, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0100] like Figure 5 As shown, device 500 includes a computing unit 501, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 502 or a computer program loaded from storage unit 508 into random access memory (RAM) 503. RAM 503 may also store various programs and data required for the operation of device 500. The computing unit 501, ROM 502, and RAM 503 are interconnected via bus 504. Input / output (I / O) interface 505 is also connected to bus 504.

[0101] Multiple components in device 500 are connected to I / O interface 505, including: input unit 506, such as keyboard, mouse, etc.; output unit 507, such as various types of monitors, speakers, etc.; storage unit 508, such as disk, optical disk, etc.; and communication unit 509, such as network card, modem, wireless transceiver, etc. Communication unit 509 allows device 500 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0102] The computing unit 501 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, and the like. The computing unit 501 performs various methods and processes described above, such as the determining state information method. For example, in some embodiments, the determining state information method can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 508. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 500 via the ROM 502 and / or the communication unit 509. When the computer program is loaded onto the RAM 503 and executed by the computing unit 501, one or more steps of the determining state information method described above can be performed. Alternatively, in other embodiments, the computing unit 501 can be configured to perform the determining state information method by any other appropriate means, such as by means of firmware.

[0103] In exemplary embodiments, the electronic device of any of the foregoing is also provided in an autonomous vehicle. For example, the on-board computer of an autonomous vehicle can be the electronic device shown in FIG. 1. Figure 5

[0104] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (PLD), a computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0105] ​Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces the functions / operations specified in the flowcharts and / or block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine as a standalone software package, or entirely on a remote machine or server.

[0106] In the context of the present disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fibers, portable compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0107] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0108] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0109] The computer system can include clients and servers. This relationship can be. The servers are typically remote from the clients with the interactions between them occurring over a communication network. The relationship between a client and a server is one of client-server. The server can be a cloud server, a server of a distributed system, or a server incorporating a blockchain.

[0110] It should be understood that the various forms of flow shown above can be re-ordered, added to, or deleted from without departing from the scope of the present disclosure. For example, the steps recited in the present disclosure can be executed in parallel, executed in sequence, or executed in a different order, as long as the desired results of the technical solutions disclosed in the present disclosure are achieved, and the present disclosure is not limited herein.

[0111] The specific implementation described above does not constitute a limitation on the protection scope of the present disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present disclosure should be included in the protection scope of the present disclosure.

Claims

1. A method of determining navigation state information, characterized by, The method comprises the following steps: forward Kalman filtering is performed on the measurement data of a global navigation satellite system (GNSS) and the measurement data of an inertial measurement unit (IMU) at N+1 time points, and the forward filtering variance and the forward state value corresponding to each time point are obtained by calculation, wherein N is a positive integer greater than or equal to 1; the forward filtering variance is smoothed respectively to obtain the smoothed forward filtering variance corresponding to each time point; wherein the smoothing processing is performed on the to-be-smoothed forward filtering variance according to the to-be-smoothed forward filtering variance and all the forward filtering variances before the time point corresponding to the to-be-smoothed forward filtering variance, and the smoothed forward filtering variance corresponding to each time point is obtained; backward Kalman filtering is performed on the measurement data of the GNSS and the measurement data of the IMU, and the backward filtering variance and the backward state value corresponding to each time point are obtained by calculation; the backward filtering variance is smoothed respectively to obtain the smoothed backward filtering variance corresponding to each time point; wherein the smoothing processing is performed on the to-be-smoothed backward filtering variance according to the to-be-smoothed backward filtering variance and all the backward filtering variances before the time point corresponding to the to-be-smoothed backward filtering variance, and the smoothed backward filtering variance corresponding to each time point is obtained; the forward state value and the backward state value are fused according to the smoothed forward filtering variance and the smoothed backward filtering variance, and the state information is obtained.

2. The method of claim 1, wherein, The method comprises the following steps: forward Kalman filtering is performed on the measurement data of a global navigation satellite system (GNSS) and the measurement data of an inertial measurement unit (IMU) at N+1 time points, and the forward filtering variance and the forward state value corresponding to each time point are obtained by calculation, wherein N is a positive integer greater than or equal to 1; forward Kalman filtering is performed on the measurement data of a global navigation satellite system (GNSS) and the measurement data of an inertial measurement unit (IMU) at N+1 time points, and the forward filtering variance and the forward state value corresponding to each time point are obtained by calculation, wherein N is a positive integer greater than or equal to 1; the forward filtering variance is smoothed respectively to obtain the smoothed forward filtering variance corresponding to each time point; wherein the smoothing processing is performed on the to-be-smoothed forward filtering variance according to the to-be-smoothed forward filtering variance and all the forward filtering variances before the time point corresponding to the to-be-smoothed forward filtering variance, and the smoothed forward filtering variance corresponding to each time point is obtained; 3. The method according to claim 1 or 2, characterized in that, the backward filtering variance is smoothed respectively to obtain the smoothed backward filtering variance corresponding to each time point; wherein the smoothing processing is performed on the to-be-smoothed backward filtering variance according to the to-be-smoothed backward filtering variance and all the backward filtering variances before the time point corresponding to the to-be-smoothed backward filtering variance, and the smoothed backward filtering variance corresponding to each time point is obtained; the forward state value and the backward state value are fused according to the smoothed forward filtering variance and the smoothed backward filtering variance, and the state information is obtained. The method comprises the following steps: forward Kalman filtering is performed on the measurement data of a global navigation satellite system (GNSS) and the measurement data of an inertial measurement unit (IMU) at N+1 time points, and the forward filtering variance and the forward state value corresponding to each time point are obtained by calculation, wherein N is a positive integer greater than or equal to 1; forward Kalman filtering is performed on the measurement data of a global navigation satellite system (GNSS) and the measurement data of an inertial measurement unit (IMU) at N+1 time points, and the forward filtering variance and the forward state value corresponding to each time point are obtained by calculation, wherein N is a positive integer greater than or equal to 1; the forward filtering variance is smoothed respectively to obtain the smoothed forward filtering variance corresponding to each time point; wherein the smoothing processing is performed on the to-be-smoothed forward filtering variance according to the to-be-smoothed forward filtering variance and all the forward filtering variances before the time point corresponding to the to-be-smoothed forward filtering variance, and the smoothed forward filtering variance corresponding to each time point is obtained; the backward filtering variance is smoothed respectively to obtain the smoothed backward filtering variance corresponding to each time point; wherein the smoothing processing is performed on the to-be-smoothed backward filtering variance according to the to-be-smoothed backward filtering variance and all the backward filtering variances before the time point corresponding to the to-be-smoothed backward filtering variance, and the smoothed backward filtering variance corresponding to each time point is obtained; the forward state value and the backward state value are fused according to the smoothed forward filtering variance and the smoothed backward filtering variance, and the state information is obtained. For each time, if the corresponding backward prediction filtering variance and the backward prediction state value are not updated, the backward prediction filtering variance and the backward prediction state value are taken as the corresponding backward filtering variance and backward state value thereof, and if the corresponding backward prediction filtering variance and the backward prediction state value are updated, the updated backward prediction filtering variance and the backward prediction state value are taken as the corresponding backward filtering variance and backward state value thereof.

4. The method according to any one of claims 1 to 3, characterized in that, The method further comprises: The measurement data of the GNSS and the measurement data of the IMU at N+1 time points are respectively acquired.

5. An apparatus for determining navigation state information, characterized by Comprise: The forward filtering module is configured to perform forward Kalman filtering on the measurement data of the global navigation satellite system (GNSS) and the measurement data of the inertial measurement unit (IMU) at N+1 time points, and obtain corresponding forward filtering variance and forward state value at each time point, wherein N is a positive integer greater than or equal to 1. The forward smoothing module is configured to perform smoothing processing on the forward filtering variance to obtain corresponding smoothed forward filtering variance at each time point, wherein the smoothing processing is performed on the to-be-smoothed forward filtering variance according to the to-be-smoothed forward filtering variance and all forward filtering variances before the corresponding time point, and the smoothed forward filtering variance at each time point is obtained. The backward filtering module is configured to perform backward Kalman filtering on the measurement data of the GNSS and the measurement data of the IMU, and obtain corresponding backward filtering variance and backward state value at each time point. The backward smoothing module is configured to perform smoothing processing on the backward filtering variance to obtain corresponding smoothed backward filtering variance at each time point, wherein the smoothing processing is performed on the to-be-smoothed backward filtering variance according to the to-be-smoothed backward filtering variance and all backward filtering variances before the corresponding time point, and the smoothed backward filtering variance at each time point is obtained. The fusion module is configured to fuse the forward state value and the backward state value according to the smoothed forward filtering variance and the smoothed backward filtering variance, and obtain state information.

6. The apparatus of claim 5, wherein, The forward filtering module is specifically configured to perform forward Kalman filtering recursion according to the measurement data of the IMU at each time, and obtain corresponding forward prediction filtering variance and forward prediction state value at each time. According to the measurement data of the GNSS, the forward prediction filtering variance and the forward prediction state value corresponding to the time of each measurement data of the GNSS are updated. For each time, if the corresponding forward prediction filtering variance and the forward prediction state value are not updated, the forward prediction filtering variance and the forward prediction state value are taken as the corresponding forward filtering variance and forward state value thereof, and if the corresponding forward prediction filtering variance and the forward prediction state value are updated, the updated forward prediction filtering variance and the forward prediction state value are taken as the corresponding forward filtering variance and forward state value thereof.

7. The apparatus of claim 5 or 6, wherein, The backward filtering module is specifically configured to perform backward Kalman filtering recursion according to the measurement data of the IMU at each time point, to obtain a backward prediction filtering variance and a backward prediction state value corresponding to each time point respectively. According to the measurement data of the GNSS, the backward prediction filtering variance and the backward prediction state value at the time point corresponding to each measurement data of the GNSS are updated. For each time point, if the corresponding backward prediction filtering variance and the backward prediction state value are not updated, the backward prediction filtering variance and the backward prediction state value are taken as the corresponding backward filtering variance and backward state value, and if the corresponding backward prediction filtering variance and the backward prediction state value are updated, the updated backward prediction filtering variance and the backward prediction state value are taken as the corresponding backward filtering variance and backward state value.

8. The device of any one of claims 5-7, wherein, The method further comprises an acquisition module configured to acquire the measurement data of the GNSS and the measurement data of the IMU at N+1 time points respectively. 9.An electronic device comprising: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-4.

10. A non-transitory computer readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to enable the computer to perform the method according to any one of claims 1-4. 11.A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-4. 12.An autonomous vehicle comprising the electronic device of claim 9.

Images